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

The description complements the annotations (readOnlyHint, idempotentHint) by detailing exactly what the call returns: MEMORY.md rules, domain indexes, environment paths, and semantic-search status. It also reinforces the intended one-time usage, which adds behavioral context beyond the bare hints. No contradiction exists with the annotations.

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 compact—two short bilingual sentences—and front-loads the most important instruction ('Call once at session start') before listing the return contents. Every phrase conveys useful information with no filler or redundancy, making it an efficiently structured description.

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?

For a read-only, idempotent tool with zero parameters and no output schema, the description covers the essential context: when to call it and what categories of data it returns. It does not specify the exact response format, but the listed content categories are sufficient for an agent to understand the tool's role in the memory system.

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 tool takes zero parameters and the schema has no properties, so there is nothing for the description to clarify about parameters. Baseline for a zero-parameter tool is met, and the description's mention of return contents implicitly indicates that this is a no-input retrieval operation.

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's purpose: it is called at session start and returns MEMORY.md rules, all domain indexes, environment paths, and semantic-search status. This concrete verb-resource pairing and explicit return list distinguish it from sibling tools like memory_get or memory_stats, which handle individual operations rather than session initialization.

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 gives an explicit temporal instruction, 'Call once at session start,' which tells the agent when this tool should be used. It stops short of naming alternatives or stating when not to use it, but the session-start context is a clear and sufficient trigger for this bootstrap operation.

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 correctly carries the full burden: it discloses that the destructive action is recoverable, records an audit tombstone, and refuses MEMORY.md. This goes beyond a generic 'delete' statement, though it omits edge behavior for nonexistent files or non-.md paths.

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?

A single sentence packs action, mechanism, recoverability, audit side effect, and a safety restriction; the bilingual version is still compact and front-loaded. No filler or repetition of schema details.

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?

For a destructive tool with no annotations and no output schema, it provides enough core context: target scope (.md), recovery trail, audit effect, and the protected file. It lacks explicit return/error behavior or what happens if the path does not exist, but these are minor for a simple delete operation.

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 67%; path and summary are already described in the schema. The description adds no new meaning to the parameters and does not clarify the agent parameter, but the parameter names and defaults make it usable.

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 names a specific action—deleting a .md file—and the mechanism (move to .trash/, recoverable) plus the audit tombstone. It clearly differentiates from sibling tools like memory_update/memory_write as a deletion operation. The explicit refusal of MEMORY.md adds precision.

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?

Usage is implied by 'delete a .md file' and the sibling set; no explicit when-to-use vs memory_update or when not to beyond MEMORY.md. It states the restriction on MEMORY.md but does not describe alternatives for cases like renaming or editing.

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?

Annotations already establish readOnlyHint and idempotentHint, so the safety profile is covered. The description adds the key behavioral output detail—that it returns domains along with their .md file counts—which is the main behavior an agent needs to know for a zero-parameter read-only listing 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?

One compact sentence (plus a parallel Chinese translation) that front-loads the verb and resource and adds only the essential output detail. No filler or schema repetition.

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?

For a zero-parameter, read-only, idempotent listing tool with no output schema, the description fully explains the return content (domains plus .md counts). There are no arguments to document and no side effects to warn about; nothing essential is missing for correct invocation.

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?

There are no parameters, so the baseline is 4. The description contributes the relevant semantic context by specifying what the returned list contains, and there is no parameter documentation gap to compensate for.

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?

States a specific verb ('List'), a concrete resource ('memory domains'), and the exact output contents (their .md file counts). This is distinct enough from generic siblings like memory_list or memory_stats because it names the domain-level aggregation rather than just listing memories or general stats.

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 choose this tool over siblings such as memory_list, memory_stats, or memory_search. The description only states what the tool does; an agent must infer when the domain-level .md count view is the right call.

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 does reveal the key behavior—flushing pending entries and reindexing—but says nothing about idempotency, side effects, locking, failure modes, or whether the operation is safe to repeat.

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 English description is a single, front-loaded sentence that communicates the action and its consequence efficiently. The bilingual duplicate adds some redundancy but does not harm 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?

For a zero-parameter action tool, the description covers the core behavior and the reindexing side effect. However, since there is no output schema and no usage guidance, an agent is left without information about expected return values or when this flush is necessary versus automatic.

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 tool has zero parameters and the input schema is completely covered at 100%, so there is nothing meaningful for the description to add about parameters. The baseline of 4 is appropriate here.

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 ('Trigger immediate distribution') and names a concrete resource ('pending write_log entries' to '.md files'), plus a clear follow-up action ('then reindex'). This distinguishes it from related sibling tools like memory_write or memory_search, making the tool's 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 phrase 'pending write_log entries' and 'immediate' imply this tool is used to force materialization of queued writes and rebuild the index. However, it never explicitly states when to use it versus memory_write or when not to use it, leaving the routing decision mostly to inference.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, so no safety disclosure is needed. The description adds path-scoping behavior (relative to memory root, bare-name convention) but does not mention error handling, truncation behavior, or return format. Given the annotation coverage, this is adequate though not rich.

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 core statement is front-loaded and compact, but the Chinese translation repeats the English content verbatim, adding no new information for an AI agent. The description could be trimmed to the English portion without losing value.

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?

For a simple 2-parameter read tool with readOnly/idempotent annotations, the description covers the crucial path format accurately. It omits max_chars and return-value details, but these are either self-evident or low-risk. Overall complete enough for an agent to invoke correctly.

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 schema has 0% description coverage, so the description carries the burden. It explains the required 'path' parameter well ('relative to memory root', bare name vs domain path), but does not mention 'max_chars' at all. The optional parameter is left entirely to inference from its name and default.

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?

States the exact operation: 'Read a single .md file by path (relative to memory root).' The examples of MEMORY.md and web/2026-08-20.md make the resource format concrete, and this is clearly distinct from siblings like memory_search (search), memory_list (list), and memory_domains.

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 the tool is for reading a known file path, and the path-resolution rules (bare name for top-level MEMORY.md, path for domain files) give clear context on how to call it. It does not explicitly name alternatives or state when not to use it, but the distinction from search/list tools is reasonably clear.

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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description only adds the 'audited' scope and path/write_log behavior. It does not disclose ordering, pagination, or entry format, but the safety profile is already covered by annotations.

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?

A single concise bilingual sentence states the verb, resource, and key scoping option with no filler or repetition.

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?

For a simple read-only, zero-required-param tool with strong annotations, the description covers the main invocation choice (path vs. whole write_log). Slight gaps remain around return format and limit semantics, but they do not prevent correct invocation.

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 50%: path is documented, while limit only has a default. The description adds meaning for path ('or the whole write_log'), but it does not clarify the semantics of limit (e.g., maximum entries) beyond the schema default.

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?

Description uses a specific verb ('Show') and resource ('audited change history' for a path or write_log). This clearly differentiates it from sibling tools like memory_get (current state), memory_search, and memory_stats.

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 purpose makes the use case inferable—history rather than current values—but there is no explicit statement of when to choose this over memory_get/memory_list or any exclusions. Usage guidance is implied by the name and description, not stated.

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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context by stating what each list entry contains (domain, chunk count, mtime) and that results can be filtered and limited, but it does not disclose ordering, wildcard semantics, or any upper bound on limit. No contradiction with annotations.

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 core action and result fields are front-loaded in the first sentence, and the parameter capabilities fit in the second. The bilingual repetition (Chinese) roughly doubles the length but is a deliberate localization choice; the English portion alone is tight with no 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?

For a simple read-only list tool with two optional defaulted parameters and annotations covering safety, the description is close to sufficient: it states the purpose, entry contents, and parameter roles. The remaining gaps—what domain="*" means, whether the domain filter is exact or wildcard, and result ordering—are material for correct invocation, keeping this at the minimum-viable level.

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 0%, so the description must compensate for the bare schema. It does add high-level meaning by mapping 'domain' to a filter and 'limit' to a cap on returned entries, which an agent can connect to the schema defaults ("*", 200). However, it leaves the matching behavior of domain unspecified (exact vs glob) and does not state what the limit default or maximum behavior entails, so compensation is partial.

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 names a specific verb ('List') and resource ('indexed files') and enumerates the per-entry fields (domain, chunk count, mtime), giving an agent a concrete idea of the operation and result shape. It does not explicitly differentiate from nearby siblings such as memory_stats or memory_domains, so it stops short of a 5.

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 gives no guidance on when to use this tool versus alternatives; with ten siblings like memory_search, memory_get, and memory_stats, an agent must infer from the name that 'list' means enumeration. The filter/limit note hints at usage for slicing results, but there are no exclusions, prerequisites, or explicit conditions for choosing this tool.

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?

Annotations already declare readOnlyHint and idempotentHint, so safety context is covered. The description adds meaningful behavioral detail beyond the schema by naming FTS5/LIKE, RRF fusion, and cosine similarity, and by stating the default modes. It does not describe how top_k, max_chars, or snippet_tokens affect result shape, but the core behavior is transparent.

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 compact and front-loaded: it opens with the action, then packs mode distinctions and filter support into a short sentence. The bilingual repetition is justified by audience needs and does not feel padded.

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 description covers the essential purpose and mode semantics, but with 7 parameters and no output schema, the missing explanations for top_k, max_chars, and snippet_tokens leave gaps. It is adequate for a basic search call but not fully complete for an agent trying to tune results or understand return 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 only 43%, so the description needed to compensate for undocumented parameters. It does add semantics for mode and domain/date_range, but top_k, max_chars, and snippet_tokens are still left to parameter names and defaults. This is partial compensation rather than complete coverage.

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 identifies the tool as 'Search memory chunks' and communicates its core differentiating feature: three search modes. It does not explicitly contrast with sibling tools like memory_get or memory_list, so it stops short of fully distinguishing from them, but the verb+resource+mode details are specific.

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 gives useful in-tool guidance: keyword is suggested for short queries, hybrid is the default, vector is pure cosine, and domain/date_range filtering is available. However, it does not explain when to choose memory_search over memory_get, memory_list, or memory_history, so the alternatives guidance is incomplete.

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?

Annotations already mark the tool as readOnlyHint and idempotentHint, so the description does not need to restate safety. It adds meaningful behavioral context by naming the categories of statistics returned, which helps the agent know what to expect beyond the annotation hints. No contradiction with annotations exists.

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 compact and front-loaded: the verb and resource appear immediately, followed by a concise list of return contents. The bilingual version adds little overhead and every phrase contributes useful information.

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?

For a zero-parameter, read-only statistics tool, the description provides a solid overview of what will be returned. However, there is no output schema, and terms like 'write log status' and 'semantic coverage' are not expanded, so an agent may not know the exact format or meaning until after calling 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?

The tool has zero parameters, so the description carries no parameter documentation burden. The baseline of 4 applies because there are no parameters whose semantics need elaboration.

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 ('Return') and a clear resource ('index statistics'), then enumerates the exact data points returned: chunk count, per-domain distribution, write log status, semantic coverage, and db size. This clearly distinguishes it from sibling tools like memory_search or memory_list, which have 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?

The description does not state when to use this tool versus alternatives, such as memory_domains for domain-specific information or memory_history for write log details. The usage context is only implied by the tool name and the nature of statistics; there is no explicit guidance or exclusions.

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 behavioral burden. It discloses useful behaviors: previous version archived under .archive/, change recorded in audit log, and refusal of MEMORY.md. However, it does not disclose the role of the 'agent' parameter, whether the file must already exist, or what happens on failure. It also doesn't state whether content is fully replaced vs merged, though 'full file content' in the schema hints at this.

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 concise: two sentences (one in English, one in Chinese) with no fluff. The core action ('Replace the content') is front-loaded, followed by side effects (archive/audit) and the critical constraint (refuses MEMORY.md). Bilingual repetition is acceptable given the schema is also bilingual, and every sentence 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 has 4 parameters, no annotations, and no output schema, the description covers the main action and key side effects but misses some context: what happens if the file doesn't exist, the role of the 'agent' parameter, and explicit guidance on when to use memory_update vs memory_write. It also doesn't describe the return value or confirmation behavior. Adequate but with clear gaps.

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 75%, with path, content, and summary having descriptions, but the 'agent' parameter has no description in the schema. The tool description does not explain 'agent' at all, which is a gap. However, the description does add context by mentioning the audit log and archive, which indirectly connects summary/agent to those behaviors. The phrase 'full file content' clarifies replacement semantics, but overall the description leaves a key parameter unexplained.

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?

Description states a specific verb ('Replace the content of an existing .md file') and resource, and distinguishes itself from siblings by explicitly excluding MEMORY.md and noting archival/audit behavior. This makes it clear how it differs from memory_write (likely creates new files) and memory_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 clearly states this is for replacing content of an existing file and explicitly mentions it refuses MEMORY.md, giving a clear when-not condition. However, it doesn't explicitly name alternatives like memory_write for creating new files, nor does it state conditions for when to choose memory_update over memory_write. The refusal condition is explicit, but other guidance is implied rather than stated.

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 of behavioral disclosure. It reveals the key non-obvious trait that this is an indirect append (not a direct .md modification), describes the log as audited, and discloses the special auto-apply behavior for network_fetch entries on flush. It does not cover permissions, failure modes, or reversibility, but the most important side-effect behavior is stated.

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 compact and front-loaded: the core behavior (append to write_log, no direct .md modification) appears immediately. The bilingual translation adds redundant length but not enough to be wasteful. Every fact present is useful, and there is minimal 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 8 parameters, no annotations, and no output schema, the description covers the central mechanism (append to a log, flush-time behavior) but leaves important gaps. It never explicitly instructs the agent to call memory_flush to apply entries, and 'distributed per config' is vague about what happens to each kind after flush. The agent can likely use the tool, but not with full confidence about downstream effects.

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 only 38%, so the description must compensate, but it provides little parameter-level detail. It adds meaning for kind=network_fetch by explaining the related web/ auto-apply behavior, but it does not explain the roles of agent, domain, task_id, ref_paths, or summary, nor does it clarify how the listed kind values map to different outcomes beyond the raw schema string.

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?

States a specific action: 'Append to the audited write_log' and explicitly contrasts itself with direct modifications: 'does NOT modify .md directly'. This clearly differentiates it from sibling tools like memory_update and memory_delete, and aligns with memory_flush. The verb+resource combination is 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 implies the intended write flow: append to the log, then have entries applied on flush. It also provides context for using network_fetch entries, but it never explicitly names alternatives like memory_update or states when to use memory_write vs. the other write-related siblings. The 'does NOT modify .md directly' warning hints at a boundary but leaves the routing to the agent.

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