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

Annotations already establish that this is a non-read-only, non-destructive, non-idempotent write, so the description's added context is what carries value: the record lands in a run history separate from the human activity feed, and it is attributed to the API key's user. The note that token cost is measured externally by the plugin hook, and that a hand estimate corrupts the data, is a genuinely useful behavioral warning. It does not say what happens on repeated calls (duplicate runs vs. update), leaving that to be inferred.

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?

Information is front-loaded — purpose first, then when to call it, then the provenance/token caveat — and the parenthetical list of non-code issue types is a compact clarification. The prose is dense and a couple of clauses (the repeated emphasis on non-code issues) could be tightened, but nothing is padding.

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 7-parameter mutation tool with no annotations on semantics and no output schema, the description covers the relevant field meanings, the attribution model, and the storage location of the result. What remains unstated is the response shape and whether re-registering the same issue creates a second run, which matters given idempotentHint=false.

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?

With only 14% schema description coverage, the description must carry the load, and it does: it explains that startedAt/finishedAt are the start and end times, that result is one of success/failure/cancelled, that summary is what was done, and that commitRef is only for commits or PRs and optional. It also explicitly discourages filling tokenCost manually. Only the issueId format is left to the schema, which already documents it well.

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 and resource ("Registra un 'run' de agente sobre una issue") and immediately scopes it to both code and non-code issues, including failed runs. It also distinguishes the artifact from the sibling-adjacent human activity feed ("historial de runs propio de la ficha, separado del feed de actividad humano"), so an agent can tell it apart from add_comment or log_time without opening a schema.

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 a clear triggering condition: register it when finishing work on the issue, and explains the consequence of skipping it ("sin run, la ficha no refleja que la trabajó un agente"). It also steers away from a misuse of the tokenCost parameter. It stops short of naming a specific alternative tool for adjacent cases, so it is clear context rather than a full when/when-not matrix.

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