Server Quality Checklist

Tool Scores

• moveB
  3.1/5.0
  Behavior2/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that the operation moves a memory entry and may rename it, but it does not disclose collision behavior, whether the destination folder must already exist, whether the original source entry is removed, or what the response looks like. For a mutating operation, these are notable gaps.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single efficient sentence that front-loads the primary action and includes the optional rename behavior. There is no filler, repetition, or unnecessary elaboration.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a relatively simple four-parameter operation with no output schema, the description and schema together cover the basic mechanics. However, it is only minimally adequate because it lacks usage guidance and behavioral side-effect disclosure, which are important when annotations are absent.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all four parameters. The description adds little beyond what the schema provides, only echoing the folder-move and optional-rename behavior. Baseline of 3 is appropriate because the schema carries the parameter-meaning burden.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific action, resource, and destination: 'Move a memory entry to another folder, optionally renaming it.' This is enough to understand the tool's core purpose. It does not explicitly differentiate from sibling tools like organize_memories, but the move operation is distinctive enough among the listed siblings.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives no guidance on when to use this tool versus alternatives. It does not mention situations where move is preferred over delete+remember, nor does it disambiguate from organize_memories, which might also reorganize memory entries. Usage context is left entirely to inference.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• bootstrap_workspaceB
  3.3/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full burden, and it does disclose what content is loaded and that recent changes are marked [new]. However, it does not disclose side-effect behavior, whether repeated calls behave differently, or any requirement to call it before other tools. The 'force' behavior is only in the schema, not the description.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One tightly packed sentence, front-loaded with 'Session bootstrap' and then listing the payload elements. Every phrase earns its place, and there is no redundant filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple bootstrap tool with no output schema and three optional parameters, the description gives a solid summary of what is returned. Yet it does not mention that calling it again during an active session may return minimal data unless force=true, and it does not orient the agent against adjacent context-loading tools. This is a reasonable but not fully complete description.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3 and the schema already documents all three parameters clearly. The description adds no parameter-specific meaning, but it does not need to compensate for missing schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('loads') and enumerates distinct resources: workspace context, essence, notes refs, and a memory index tree with [new] markers. It clearly communicates what the tool does, though it does not explicitly contrast itself with related sibling tools like get_current_workspace or load_more_context.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The phrase 'Session bootstrap' implies this is the initial context-loading call, but there is no explicit guidance on when to use it versus sibling tools such as load_more_context, load_turn_context, or get_current_workspace. No alternatives or exclusions are mentioned, leaving the agent to infer usage timing.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• recallB
  3.3/5.0
  Behavior2/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Read' and mentions key/folder; it does not describe return format, behavior for missing keys, default folder handling beyond the schema, or whether the operation is purely local with no side effects. This is minimal disclosure.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, focused sentence that leads with the action and resource, then the selection criteria. It contains no filler, repetitions, or irrelevant details, while still being sufficiently informative for such a simple operation.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple read tool with two parameters and no output schema, the description is adequate but thin. It covers the core operation and parameters, but lacks guidance on expected return values, error behavior, or when to use this instead of the many sibling memory tools. The absence of annotations increases the need for more behavioral context than is provided.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents both 'key' and 'folder' adequately. The description simply restates 'by key and folder' without adding extra semantic meaning, such as key format, folder path rules, or what constitutes a valid memory entry. This matches the baseline for full schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('Read') and resource ('memory entry') with a precise selection mechanism ('by key and folder'). It is unambiguous and immediately understood, though it does not explicitly call out how it differs from siblings like 'search' or 'list' beyond the key-based nature of the operation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool should be used when you already know the key and possibly the folder of a memory entry. However, it does not explicitly state when to prefer this over 'search' or 'remember', nor does it mention alternatives or exclusions, leaving usage context to inference.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• organize_memoriesB
  3.4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full burden and does disclose meaningful stateful behavior: empty call is a read returning essence, pending files, and rules; content call writes essence.md. However, it never discloses write semantics — whether storing overwrites or merges the existing essence, or what happens to 'pending memory files' after incorporation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, roughly 25 words, with the core concept front-loaded and each stage explained in one clause. Every sentence earns its place; a brief note about when this stage should be triggered would make it fully self-contained.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The two-stage behavior is captured, but for a stateful write tool with no annotations and no output schema, the definition omits important context: overwrite/merge semantics, the lifecycle of pending memory files, prerequisites like workspace bootstrapping, and routing relative to the memory siblings. It is adequate with clear gaps.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline of 3 applies; the schema already documents that content is a Markdown body with inline citation format and that sources is a tracking list of memory/ keys. The description adds light context by tying content to the essence.md artifact, but offers no parameter detail beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names the resource (workspace memory) and spells out two concrete operations: an empty call returns 'existing essence + pending memory files + rules,' and a content call stores 'the organized essence.md.' This distinguishes it from retrieval-only siblings like recall and search. However, the primary action is framed as a noun phrase ('organizer') rather than an explicit directive verb.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives conditional usage guidance for its own two modes (empty vs. with content), which is useful. But with 19 sibling tools, it never states when to use this consolidation workflow versus alternatives like remember or recall, leaving routing entirely to inference.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• searchA
  3.5/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  It adds a useful behavioral detail—case-insensitive matching—beyond what the input schema states. However, no annotations are provided, and the description does not disclose whether the search is read-only, how results are returned, whether partial matches are supported, or if there are result limits.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One short, front-loaded sentence with no fluff: the action, target, and key behavioral trait are all stated immediately. Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple two-parameter search tool, the description is adequate for basic invocation, especially given full schema coverage. However, with no output schema, no annotations, and closely related sibling tools ('search_context', 'recall'), the description could be more complete by noting result shape, limitations, or a pointer to alternatives.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so parameter names and descriptions already document 'query' and 'folder'. The description adds context by specifying that the query searches titles and contents case-insensitively, but it adds no detail about query syntax, wildcards, or folder path format beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('search'), a resource ('memory titles and contents'), and a behavioral qualifier ('Case-insensitive'). It clearly distinguishes from list-like siblings, but it does not explicitly distinguish itself from closely related siblings such as 'search_context' or 'recall'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool is for keyword matching over memory titles/contents, but it gives no explicit guidance on when to prefer it over alternatives like 'search_context' or 'recall'. It states what it searches, but not when it should or should not be used relative to siblings.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• trace_themeA
  3.6/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full burden of behavioral disclosure. It does disclose that results are sorted by time and returns associated turns and memories, but it does not explicitly state whether this is a read-only operation or describe any side effects, performance implications, or data-loading behavior beyond the schema.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two short sentences with zero wasted words. The core purpose is front-loaded, and the return behavior is stated succinctly in the second sentence.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple two-parameter tool with no output schema, the description adequately explains what is returned and how it is ordered. It is missing some context about possible limitations or when to prefer another tool, but it is broadly complete for the tool's complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents both parameters. The description adds no additional meaning about 'theme' or 'includeTurnContent' beyond what the schema provides, so the baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('Trace'), a resource ('evolution of a theme across sessions and memories'), and the output ('associated turns and memories sorted by time'). This distinguishes it from siblings like search or recall, which imply broader retrieval rather than temporal theme evolution.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives no explicit guidance on when to use this tool versus alternatives such as recall, search_context, or list_themes. The only usage signal is implied by the word 'Trace,' but there are no exclusions, prerequisites, or comparisons to other tools.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• refine_session_turnsA
  3.7/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description must carry the behavioral burden. It does disclose a side effect: 'Output is written to refined/<sessionId>.jsonl' and implies the source file is only read. However, it does not mention whether the output file is overwritten or appended, what the tool returns, or any other side effects.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences convey the action, input, and output destination without wasted words. The most important details are front-loaded, and each clause earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with no annotations and no output schema, the description is adequate but has clear gaps: it does not describe the return value, file overwrite behavior, or what the refined JSONL will contain. The optional parameters are documented in the schema, so that part is covered.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already explains each parameter. The description adds no parameter-level detail beyond naming the output path, which partially clarifies sessionId's role. No compensation is needed, but no bonus either.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb-resource pairing: 'Read a session wire.jsonl' and 'generate Refined Turn Summaries.' It also names the output destination, clearly distinguishing this tool from siblings like load_turn_context and organize_memories. The action and artifact are unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The usage context is implied rather than explicit: use this when you need Refined Turn Summaries for a session. It does not state when to avoid this tool or mention alternatives, even though several siblings deal with session/memory context.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• rememberA
  3.7/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations are absent, so the description carries the full disclosure burden. It does disclose the mutation and destructive-overwrite behavior ('Write or overwrite') and the file format, which is genuinely useful context an agent cannot get elsewhere. However, it does not state what happens to an existing entry beyond overwriting it, whether the action is reversible, or any side effects such as workspace index updates.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single 16-word sentence that front-loads the verb and resource, then packs in the storage format. There is zero filler; every word contributes, and the essential action is immediately visible.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a mutation tool with no annotations and no output schema, the one-line description leaves gaps: no return value information, no warning about the overwrite consequence, and no guidance on when creating vs. overwriting is appropriate. The rich schema compensates substantially for content structure, making this minimally adequate but not complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, and the schema already documents every parameter — including an unusually detailed content parameter with per-type examples for decisions, rules, knowledge, and references. The tool description's mention of YAML frontmatter aligns with the tags/themes parameters but adds no new parameter semantics beyond what the schema already provides, so the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States a specific verb pair (write/overwrite), a clear resource (memory entry), and the storage format (Markdown file with YAML frontmatter). This clearly differentiates it from sibling read/search tools like recall, search, and list, and from management tools like delete, move, and organize_memories — an agent can tell them apart without opening schemas.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No explicit when-to-use or when-not-to-use guidance, and no sibling alternatives are named. The write/overwrite verb implies it is for persisting memories while recall/search are for retrieval, but an agent must infer that. The detailed content parameter description covers content formatting for decisions/rules/knowledge/references, but that addresses what to write, not when to choose this tool over alternatives.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• deleteA
  3.8/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly conveys the destructive nature of the action ('Delete') and the scoping via folder, but does not mention irreversibility, error behavior, or side effects. This is adequate for a simple delete but not detailed.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single concise sentence that front-loads the verb and includes both relevant parameters. Every word earns its place, with no filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's simplicity—2 parameters, no output schema, no nested objects—the description plus full schema coverage provide sufficient information for correct invocation. A note on default folder behavior or consequences would be valuable, but is not essential for a basic delete operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the input schema already documents key and folder with descriptions. The description adds 'by key and folder', which aligns with the parameters but does not provide additional semantic meaning beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('Delete') and resource ('memory entry'), and specifies the targeting criteria ('by key and folder'). It distinguishes this tool from sibling tools like delete_search_view and delete_theme by indicating it operates on memory entries.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage for deleting memory entries by key and folder, which is a clear operational intent. However, it provides no explicit when-to-use guidance or comparison to alternatives such as move or organize_memories, leaving some room for interpretation.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• delete_themeA
  3.8/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the burden and does disclose the key boundary: referenced refined turns and memories are preserved. However, it does not mention permanence, side effects on lists/indices, or permission requirements, leaving gaps.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two short sentences with no filler; the primary operation is front-loaded and the crucial side-effect clarification follows immediately.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a one-parameter operation with no output schema and full schema coverage, the description is largely complete: it states the action, the affected resource, and what is not affected. Only minor details like reversibility are absent.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already fully describes theme as 'Theme identifier to delete' (100% coverage), and the description adds no additional format, source, or usage detail. Baseline 3 applies because the schema handles the parameter documentation.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states the exact action (delete a theme association file) and explicitly scopes it: it does not delete refined turns or memories. This distinguishes it from the generic sibling delete and tells an agent precisely what resource is affected.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool is for removing just the theme association while preserving referenced turns/memories, but it does not explicitly say when to prefer it over the similarly named delete or tag_theme/trace_theme siblings. Usage context is inferable, not stated.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• list_themesA
  3.8/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the burden of behavioral disclosure. 'List' reasonably implies a read-only, non-destructive operation, and 'identifiers' clarifies the granularity of results. However, it does not disclose ordering, failure behavior, or whether the operation accesses persistent storage or memory, which would add useful transparency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single concise sentence that front-loads the core action and resource. Every word contributes meaning, with no filler or redundant detail.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter tool, the description is nearly complete: it states the action, result granularity, and workspace scope. The absence of an output schema means the description could optionally specify the return format, but 'list theme identifiers' adequately conveys that the result is a collection of identifiers.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters and an empty schema, so there is nothing to document. Baseline 4 applies because no parameter explanation is needed and the description is not missing any parameter semantics.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('List'), a precise resource ('theme identifiers'), and a scope ('current workspace'). This clearly differentiates it from the sibling tool 'list_tags', which targets tags rather than themes.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use the tool (when you need all theme identifiers), but it provides no explicit guidance about when not to use it or when a sibling tool like 'tag_theme', 'trace_theme', or 'search' would be more appropriate. No alternatives or exclusions are mentioned.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• load_turn_contextA
  3.8/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the transparency burden; 'load' clearly conveys a retrieval/non-mutating operation and 'full detailed content' sets expectations about output richness. However, it does not describe return format, scoping rules, or any behavioral caveats (e.g., unavailable turns), which would be valuable given the absent annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The entire description is one focused sentence with the action and resource front-loaded; every phrase contributes to identifying the tool's target and selection method. No filler or redundant restatement.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple one-parameter retrieval tool with no output schema, the description explains what the agent gets ('full detailed content') and how to address turns ('by sessionId and turnId'). It is slightly incomplete on what the returned content looks like for multiple references, but it is otherwise sufficient given the low complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already describes the references array and its sessionId/turnId properties at 100% coverage, so the description adds little parameter-specific meaning beyond reiterating the identifier-based selection. This meets the baseline for high schema coverage but does not exceed it.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names a precise verb ('load'), a specific resource ('specific conversation turns'), and the exact selection keys (sessionId and turnId). This clearly differentiates it from memory search/list siblings: it is a targeted fetch by explicit identifiers, not a discovery tool.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The phrase 'by sessionId and turnId' implies the tool is appropriate when the agent already has exact conversation identifiers and needs full details, so usage context is implied rather than stated. It does not explicitly mention alternatives such as search_context or load_more_context, nor does it state when not to use it.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• tag_themeA
  3.8/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the burden of behavioral disclosure. It does reveal the significant auto-create-theme behavior, but it does not explain what happens when multiple optional targets are provided, whether the operation is idempotent, or what the return value is.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and every sentence carries relevant information, including the semantic requirement and auto-creation. The main action is not front-loaded; it appears after a conditional clause, which is a minor structural inefficiency.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description covers the core operation and the auto-create behavior, which is enough for basic invocation. However, it does not explain parameter selection when both turn and memory fields are available, nor what the tool returns, leaving some ambiguity for an agent given the six-parameter schema and no annotations.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  All six parameters already have clear schema descriptions, so the baseline is 3. The tool description adds no parameter-specific detail and even narrows the scope to turns while the schema also supports memory attachment, though the schema itself clarifies those fields.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action: attaching a turn to a theme after confirming semantic relevance. It explicitly distinguishes the operation from keyword-based tagging and discloses automatic theme creation, making the purpose specific and unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives strong usage guidance: only attach when the content genuinely belongs to the theme, and never on keyword match alone. It does not explicitly route the agent to sibling tools, so it falls just short of a 5.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• delete_search_viewA
  4/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description clearly discloses the destructive action and the conditional removal of refined turns referenced by the view. It also provides a rationale for the flag, though it does not mention irreversibility or permission requirements.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description consists of two efficient sentences: the primary action is front-loaded, and the optional behavior is explained in the second sentence. There is no filler or redundant detail.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the low complexity, the description covers the core behavior and optional side-effect while the schema handles parameter details. It omits guidance on locating view keys (e.g., via list_search_views) and on the permanence of deletion, but these are not critical for a simple delete operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds only the rationale 'purging low-quality refined data' for deleteRefinedTurns and does not add information about the key parameter beyond what the schema already provides.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('delete') and resource ('saved search view'), making the tool's function clear and unambiguous. It also mentions the optional deletion of refined turns, which helps distinguish it from generic sibling tools like 'delete'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies this tool should be used to delete saved search views but gives no explicit guidance on when to use it versus alternatives or exclusions. The only usage direction is for the optional deleteRefinedTurns flag, not for selecting this tool over others.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• get_current_workspaceA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the full burden. It clearly enumerates the return values, which implies a read-only operation, but it does not explicitly state that there are no side effects, nor does it clarify what 'current' means or how failures are handled. For a simple getter this is adequate but not fully transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single, front-loaded sentence with no filler. Every word earns its place, and the three return items are listed succinctly.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter, read-only getter, the description covers the essential information: what it returns. The absence of an output schema is mitigated by the explicit enumeration of returned fields. It might additionally state that no modifications occur, but the tool's simplicity makes this less critical.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has zero parameters, so the baseline is 4. There are no parameter details needed; the description correctly focuses on return values.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Return') and identifies the exact resource: current cwd, workspace id, and store path. There is no ambiguity about what the tool does, and it is easily distinguished from the sibling tools, none of which target the current workspace.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description states what the tool returns but does not explicitly explain when to use it versus alternatives. The intended use is implied by the tool's unique purpose and zero parameters, but there is no direct guidance or mention of exclusions.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• listA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the full burden. It discloses the sort order but does not explicitly state that the operation is read-only, whether pagination exists, or what fields are returned for each entry. These are only lightly implied by the word 'List'.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One concise sentence front-loads the core verb and resource, then appends the sort order. Every word adds information and there is no irrelevant detail.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple listing operation, the description plus the fully documented schema are sufficient to invoke the tool correctly. The only missing context is explicit guidance about when to prefer this over search/recall, which is a secondary gap given the tool's low complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  All three parameters have descriptive schema entries (100% coverage), so the description adds no additional param semantics. The baseline of 3 applies because the schema already documents tag, limit, and folder.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names a specific verb ('List'), resource ('memory entries'), scope ('the workspace'), and ordering ('most recently updated'), which fully clarifies what the tool does. This distinguishes it from sibling listing tools such as list_tags and list_themes, which target different resources.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The intended use is stated directly: list memory entries in the current workspace, with optional tag/folder filters. It does not mention alternatives like search or recall, so some selection nuance is left to the agent, but the core use case is clear.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• list_search_viewsA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the full behavioral burden. It discloses that views are persisted records tied to search_context calls, which is useful context, and 'List' implies a read-only operation. However, it does not explicitly state side-effect-free behavior or any ordering/pagination details beyond the schema's 'recent views' hint, leaving some behavioral ambiguity.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three short sentences, each adding distinct value: the core purpose, the definition of a view, and the practical use case. It is front-loaded with the action, has no redundancy, and every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple list tool with one optional parameter and no output schema, the description covers what the tool returns (views), why the data matters (clusters from search_context), and when it should be used (before creating/extending a theme). It does not describe the exact fields of a view, but the low complexity and clear naming make this a minor gap.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The only parameter, 'limit', is already fully described in the schema as 'Maximum number of recent views to return.' Since schema description coverage is 100%, the description does not need to add parameter detail, and it does not. This meets the baseline for schema-covered parameters.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a precise verb and resource, 'List saved search views,' which is unambiguous. It further distinguishes the tool by explaining that a view records clusters from a previous search_context call, setting it apart from siblings like list_tags and list_themes.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear contextual guidance: 'Use these views as candidate sets before creating or extending a theme.' This tells the agent when to use the tool, though it does not explicitly name alternatives or state when-not-to-use conditions, so it stops short of a full 5.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• list_tagsA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  There are no annotations, so the description carries the behavioral burden. 'List all tags' signals a read-only operation, but it does not disclose return format, ordering, whether tags include metadata, or any potential limitations. This is adequate for a simple list operation but not deeply transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single concise sentence with no filler or redundant phrasing. Every word adds meaning, and the key scope ('current workspace') is included.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter read tool, the description is mostly complete: it states the action, resource, and scope. It lacks output format details, but no output schema is provided, so an agent may not know the exact response shape. Still, it is sufficient to select and invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters, so no parameter documentation is needed. The baseline for zero-parameter tools is 4, and the description adds sufficient context by clarifying the scope as 'current workspace.'

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('List') and resource ('tags'), and scopes it to the current workspace. It clearly distinguishes from sibling tools like list_themes and generic list.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The use case is implied: call this tool when you need the tags in the current workspace. However, there is no explicit guidance about when to prefer this over related tools such as list, search_context, or list_themes.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• load_more_contextA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the burden. It does disclose the key behavioral trait that rounds are 'summarized' and that the source is the 'active wire.jsonl', but it does not mention read-only behavior, limits, default values, or potential side effects. This is acceptable but not fully transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, compact sentence with no filler. It front-loads the action and resource, then adds the key qualifiers: 'summarized' and 'before a given turn id'. Every element contributes to understanding.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a relatively simple tool with two well-documented parameters, the description is mostly complete. It conveys source, output style, and the core selection criterion, though it could optionally clarify return format or default limits since there is no output schema.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents both parameters well. The description adds useful context about 'older rounds' and 'before a given turn id', but does not add substantial new parameter meaning beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('Load'), a specific resource ('older conversation rounds from the active wire.jsonl'), and a scoping condition ('before a given turn id'). The 'summarized' qualifier further distinguishes it from tools that return raw context or current turn context.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description clearly implies when to use this tool: when older, summarized conversation rounds are needed relative to a specific turn. It does not explicitly name alternatives or exclusions, but the context is clear enough for an agent to select it appropriately among siblings.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• search_contextA
  4.1/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the disclosure burden. It usefully reveals output-budget behavior and how detail levels change the returned content. It does not mention side effects, but 'search' implies a read operation, and the key truncation behavior is clearly disclosed.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three sentences with the primary action front-loaded, followed by concise detail-mode guidance. Every sentence adds useful information and there is no filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a search tool with full schema parameter coverage, the description supplies the missing behavioral context: output size, detail-level trade-offs, and cluster-member visibility. It does not describe the result shape for empty results or explicitly address sibling alternatives, but overall it is sufficient for an agent to select and invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3, but the description adds practical meaning beyond the schema by explaining the trade-offs among compact, normal, and full detail, and by tying normal mode to the 6000-char output budget. This helps an agent choose the right parameter value.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb and resource: search conversation rounds across all workspace session wires by keywords and optional date range. It is specific enough to convey the tool's scope, though it does not explicitly differentiate itself from sibling tools like 'search' or 'recall'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives practical guidance on when to use each detail level: compact for a quick overview, normal as the default with a ~6000-char output budget, and full when complete match text and cluster members are needed. However, it does not explicitly state when to use this tool instead of alternative siblings.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• sync_workspace_indexA
  4.2/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full behavioral burden. It discloses that an empty call is a read/report operation and that folderComments triggers a write-like action, but it does not state whether changes are persistent, reversible, or what side effects 'set folder descriptions' has on index.json. Some behavior is implied but not fully transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences with no filler. The main operation is front-loaded, and each sentence communicates a distinct usage mode. Nothing is redundant.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with one optional parameter and no output schema, the description covers both invocation modes and their intended effects. It is slightly incomplete in describing what 'reports mismatches' returns and what exactly gets updated, but it provides enough for an agent to call the tool correctly in either mode.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining the effect of folderComments ('to set folder descriptions') and contrasting it with the empty-call behavior. This exceeds what the schema alone provides.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Reconciles index.json with the filesystem.' It also clarifies the two operational modes, so there is no ambiguity about what the tool does or how it differs from the memory- and search-oriented siblings.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly distinguishes when to call without arguments ('Empty call scans and reports mismatches') and when to provide folderComments ('to set folder descriptions'). It does not mention alternatives or when-not-to-use this tool relative to siblings, so it falls just short of a 5.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• open_memory_dashboardA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full behavioral burden. It discloses that the tool opens the default browser and starts the server if needed, covering both observable side effects. It could mention potential blocking or return behavior, but for this simple action it is mostly sufficient.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two short sentences with no filler. The primary action is front-loaded, and the conditional server-starting behavior is added as a useful secondary detail.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter tool with no output schema, the description is complete. It tells the agent exactly what will happen and the only relevant condition, making it sufficient for invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has zero parameters, and the baseline for 0-parameter tools is 4. There are no parameter semantics to add, and the description does not need to document parameters that do not exist.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb ('Opens'), the resource ('memory dashboard'), and the medium ('in the default browser'). It also adds the server-starting behavior, which fully distinguishes it from the sibling memory tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context for when to use the tool: when the memory dashboard needs to be opened in a browser. It does not mention alternatives or exclusions, but no sibling tool appears to provide the same capability.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.