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

Annotations only supply the generic mutation/idempotency profile, and the description adds real behavioral detail: over-length task_summary is stored shortened with a warning and never refused (so retries are pointless), files are capped at 60, and the server cannot see the caller's filesystem. It does not explain what the stored entry looks like or rejection conditions beyond summary length, so it stops short of 5.

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?

Front-loads purpose in the first sentence, then the when-to-call rule, then parameter caveats. Four dense sentences with no filler, though the parameter guidance is packed tightly enough to be slightly hard to scan.

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 an 11-param, nested-object mutation tool with no output schema, the description covers the trigger, the cardinality rule, and the failure/truncation behaviors that matter most for correct invocation. Gaps remain around the taxonomy enums and the optional verbose/operation_id interplay, but the core call path is well covered.

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 55%, and the description compensates for the least self-documenting parameters: task_summary should be one sentence under ~300 chars, and files_touched paths must be workspace-relative. It adds nothing for the enum params (domain/action/scope), which the schema already constrains, leaving some residual gap.

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 (log) and resource (a file-modifying response/activity entry) with the payload scope ('structured taxonomy and file paths'). The resource is unique among siblings, which are all memory/rule/skill CRUD tools, so an agent can route to it unambiguously.

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?

Explicit trigger ('Call this AFTER every response where you created, edited, or deleted files') plus a frequency constraint ('one call per response, not per file') that rules out the obvious misuse. No alternative tool exists for this purpose, so no alternative-routing text is needed.

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