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

The description explains the main behaviors (duplicate detection, fact promotion, pruning, report writing) but lacks detail on side effects, risk of data loss from pruning, or performance implications. With no annotations, more context about safety or permissions would be helpful.

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

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

The description is a single concise sentence that front-loads the overall purpose ('Full memory graph maintenance') and lists specific actions. It is focused and avoids verbosity, though it could be slightly more structured (e.g., separating actions).

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

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

Given no output schema and no annotations, the description is incomplete. It does not describe what the maintenance report contains, whether the tool should be run periodically, or how it interacts with sibling memory operations. More context would be needed for an agent to decide confidently when to invoke it.

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

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

Only one parameter (dryRun) with full schema description (100% coverage). The tool description does not add any information about the parameter beyond the schema. Baseline 3 is appropriate as the schema already documents it adequately.

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

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

The description uses a specific verb ('consolidate') and resource ('memory graph maintenance') and lists concrete actions: finding duplicates, promoting facts, pruning stale observations, writing a report. It clearly distinguishes from sibling tools like recall, remember, link, etc., which are individual memory operations rather than maintenance.

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

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

No guidance on when to use this tool vs alternatives. It does not specify prerequisites, frequency, or conditions under which maintenance should be run. Sibling tools are listed but no comparison or exclusions are provided.

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

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 only states the action (removal) without detailing side effects, required permissions, what happens if the entity or observation does not exist, or whether the operation is reversible. The description is minimally informative.

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

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

The description is a single, front-loaded sentence of 11 words that efficiently conveys the core action. It wastes no words, though it could incorporate a bit more contextual detail without becoming verbose. Still, it earns its place.

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

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

Given the tool's simplicity (2 required parameters, both documented, no output schema), the description combined with the schema covers the basic operation. However, it lacks behavioral details such as success/failure behavior or exact match requirements, which are partially inferred from the schema but not explicitly stated in the description.

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

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

Schema coverage is 100% with both parameters already described (entityName and observation). The description adds no additional meaning beyond what the schema provides, so a baseline of 3 is appropriate. No extra constraints, formats, or usage hints are given.

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

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

The description uses a specific verb ('Remove') and clearly identifies the resource ('a specific observation from an entity in the memory graph'). This directly distinguishes it from sibling tools like 'remember' (add) and 'recall' (retrieve), making the purpose unambiguous.

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

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

The description provides no guidance on when to use this tool versus alternatives such as 'remember' or 'link'. It does not mention prerequisites, error conditions, or scenarios where this tool is inappropriate, leaving the agent without explicit decision support.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It only says 'Returns' without clarifying whether the operation is read-only, requires authentication, has side effects, or rate limits. The description is too brief to convey behavioral traits beyond the basic function.

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

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

The description is a single sentence that is front-loaded with the core action. Every word is necessary; there is no redundant or filler content. It achieves maximum conciseness without sacrificing clarity.

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

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

The tool has no output schema, so the description should explain what a 'Convention entity' looks like or the return format (e.g., list, object, pagination). The current description is too sparse to fully inform an agent about the tool's behavior, especially given the sibling tools suggest a memory graph context.

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

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

Schema description coverage is 100%, with the 'domain' parameter already described as 'Optional keyword to filter conventions (e.g. 'Notion', 'Linear', 'API')'. The description adds only a paraphrase ('optionally filtered by domain keyword'), offering no additional meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool returns 'Convention entities from the memory graph', which is a specific verb and resource. It distinguishes itself from sibling tools like 'recall' (generic memory retrieval) or 'get_identity' by focusing on conventions.

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

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

The description mentions optional filtering by domain keyword, giving a usage hint. However, it does not explicitly state when to use this tool over alternatives like 'recall' or when not to use it (e.g., if no conventions exist). Guidance is implied but not fully explicit.

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

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 accurately states that the tool returns identity and the first 3000 characters of MEMORY.md, revealing exactly what the agent will receive. No side effects or hidden behaviors are implied.

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

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

Two sentences with no wasted words. The first sentence states the purpose, the second provides usage context. Information is front-loaded for quick parsing.

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

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

Given no output schema, the description adequately explains the return value. It covers identity and memory content length. Could mention that it is read-only and safe to call multiple times, but this is not critical for a simple info-retrieval tool.

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

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

The input schema has zero parameters, so schema description coverage is 100%. The description does not need to add parameter information. The baseline score of 4 is appropriate since there are no parameters to document.

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

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

The description clearly states it returns 'the agent's identity (SOUL.md) and the first 3000 characters of MEMORY.md'. This is a specific verb+resource combination that distinguishes it from siblings like 'recall' or 'get_conventions', which serve different purposes.

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

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

Explicitly tells the agent to 'Use at the start of a session to establish context.' This provides clear when-to-use guidance. However, it does not mention when not to use it or alternative tools, though for a context-setter this is acceptable.

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

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

With no annotations, the description fully informs about behavior. It discloses that duplicate relations are skipped, implying idempotency. However, it does not specify what happens if the 'from' or 'to' entities do not exist in the graph, or whether the operation is reversible. This leaves moderate gaps for a mutation tool.

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

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

The description is extremely concise at two short sentences. The purpose is stated first, followed by a critical behavioral note. Every word serves a purpose – no fluff, no repetition of schema details. This is ideal for quick agent comprehension.

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

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

Given the lack of annotations and output schema, the description is adequate but incomplete. It covers the action and duplication behavior, but omits what the tool returns, error scenarios, and prerequisites (e.g., entity existence). For a simple three-parameter tool, these gaps are noticeable but not crippling.

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

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

The input schema has 100% description coverage for its three parameters. The description adds no extra meaning beyond the schema – it reiterates the concept of relating entities but does not provide examples, formatting hints, or constraints like case sensitivity. Following the baseline for high coverage, a 3 is appropriate.

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

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

The description clearly states the action ('Add a relation'), the resource ('relation between two entities in the memory graph'), and a key behavior ('Duplicate relations are skipped'). This is a specific verb-resource combination that distinguishes 'link' from sibling tools like 'recall', 'remember', or 'forget', which handle different aspects of memory.

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

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

No explicit guidance is provided on when to use this tool versus alternatives. For instance, it does not clarify that 'link' should be used after creating entities with 'remember', or that it is not needed if entities don't exist. The description implies usage by naming the resource, but lacks direct context or exclusion criteria.

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

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

No annotations are provided, so the description carries the full burden for behavioral traits. It correctly describes the read-only nature (search and return) and what is returned (matching entities with observations and relations). However, it does not disclose edge cases like empty results, behavior with partial matches, or whether the search is case-sensitive or fuzzy. A 3 is appropriate as it covers the basic safety profile but lacks depth.

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

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

The description is two sentences long, front-loaded with the action and subject, and contains no fluff. Every clause adds value: first sentence states the main purpose, second sentence clarifies the result format.

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

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

Given the tool has only 2 parameters (both documented with 100% schema coverage), no output schema, and moderate complexity, the description is reasonably complete. It covers the tool's purpose, the resource type, and the return structure. A 4 reflects that no output schema exists but the description adequately describes what is returned.

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

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 does not add any parameter specifics beyond what the schema already provides (e.g., the default limit value or that query matches against names, types, and observations are already in the schema). No additional semantics are contributed.

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

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

The description clearly states the tool searches the memory graph for entities matching a query and returns them with observations and relations. It specifies the verb 'search', the resource 'memory graph', and the granularity of results, distinguishing it from siblings like 'remember' (store) or 'forget' (delete).

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

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

The description implies this is the tool to use for retrieval queries against the memory graph. However, it does not explicitly state when to use this versus other retrieval siblings like 'get_identity' or 'get_conventions', nor does it mention when not to use it or provide alternatives for more specific searches.

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

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

With no annotations provided, the description carries the full burden. It clearly explains the upsert semantics (merge vs overwrite) and the default behavior. However, it does not disclose any side effects, error conditions, or prerequisites (e.g., whether the entity must exist for certain operations).

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

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

The description is extremely concise: two sentences that immediately state the action and the key behavioral nuance. Every word is necessary, and there is no repetition or filler.

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

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

Given the tool's simplicity (4 parameters, no output schema, shallow nesting), the description covers the essential behavior. Missing details like error handling or return value are acceptable given the scope, but the description could be slightly more explicit about creation vs update behavior for new entities.

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

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

All four parameters have schema descriptions (100% coverage), so the baseline is 3. The tool description does not add any additional meaning or context about the parameters beyond what the schema already provides.

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

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

The description clearly states the verb 'Upsert' and the resource 'entity in the memory graph', and explains the merge vs overwrite behavior based on the 'upsert' parameter. This distinguishes it from siblings like 'recall' (read) and 'forget' (delete) without ambiguity.

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

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

No guidance is provided on when to use this tool versus alternatives such as 'store_decision' (which might be more specific) or 'link' (for relationships). The description only explains the mechanism, not the selection criteria.

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

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

With no annotations, the description carries the full burden of disclosure. It reveals that a Decision entity with a dated observation is created, but omits behavioral details such as whether existing decisions are overwritten, required permissions, or side effects on the memory graph. The word 'store' implies a write operation, but no further transparency is given.

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

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

The description is a single, short sentence with no redundant words. It efficiently conveys the core action and entity type.

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

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

The tool has 4 parameters, no output schema, and no annotations. The description does not explain the 'memory graph' context, what a 'dated observation' entails, or how returned data looks. Sibling tool names provide some context but are not referenced. The description is insufficient for an agent to fully understand the tool's behavior.

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

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

Schema description coverage is 100%, so parameters are well-defined in the schema. The description adds no additional meaning for any parameter (e.g., what 'dated observation' means for 'content' or how 'importance' affects storage). Baseline of 3 is appropriate.

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

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

The description clearly states the action 'Store' and the resource 'an important decision in the memory graph as a Decision entity with a dated observation.' It differentiates from siblings like 'remember' by specifying the entity type, though it does not explicitly distinguish usage from similar tools.

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

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

No guidance is provided on when to use this tool versus alternatives like 'remember' or 'recall.' The description does not mention prerequisites, context, or exclusions, leaving the agent without decision-making support.

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