record_update

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

With no annotations, the description carries the full load; it does disclose meaningful traits: append-only semantics, idempotent retry behavior via request_id, and the fact that no code inspection or test execution occurs. It does not cover permission/auth requirements, what happens when a duplicate request_id arrives, or what the call returns (no output schema), leaving real gaps for a write 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?

Three short sentences, each doing distinct work: the action and kinds first, then field-filling guidance, then the non-execution boundary. No filler, no repetition of the schema, and the most important information is front-loaded.

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 nine-parameter, 0%-coverage, annotation-free write tool with no output schema, the description covers the high-value fields but omits the identity/scoping parameters and any indication of the response. It is workable but leaves enough unaddressed that an agent may guess at project_id/agent_id/task_id semantics.

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: it explains request_id (retry safety), details (rationale/tests/next steps), files (relative paths) and git_ref (commit/branch), and enumerates the kind values. However, three of nine parameters — project_id, agent_id, and task_id — get no explanation at all, so coverage is partial for a nine-parameter tool.

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 ("append") and the record types it accepts, listing the exact kinds (progress, decision, handoff, blocker, test, note) that map to the `kind` enum. It is clearly a write of an update entry, distinguishable from read siblings like get_updates and from task-mutation siblings like update_task, though it never names those siblings explicitly.

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?

Gives concrete guidance on how to call it (use request_id for safe retries; put rationale/tests/next steps in details; reference relative files and a commit/branch) and one clear boundary ("does not inspect code or execute tests"), which steers agents away from expecting verification. It stops short of stating when to prefer this over update_task or when a record should not be written at all.

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