complete_task

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

With no annotations, the description carries the full burden and does disclose key behavioral traits: multiple refusal conditions (missing evidence, unpushed commits, failed last test run) and a `force` override. What it omits is permission/auth requirements, idempotency, and what a rejection returns, so it is strong but not complete.

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?

It is compact, but the telegraphic, semicolon-chained phrasing ('Done means live', 'the rest to come') and backtick-spliced identifiers make it hard to parse and it is not cleanly front-loaded with the primary action. Compactness here comes partly at the cost of readability.

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 8-parameter, nested-object mutation tool with no annotations and no output schema, the description covers refusal semantics and several parameters well but leaves `pr`/`full` semantics and the response behavior unstated. It is adequate on the gating logic yet incomplete for the tool's full surface.

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% across 8 parameters, so the description must compensate. It meaningfully explains `evidence` (criterion-id to link/version/check map), `partial`, `remains`, `force`, and `review`, but leaves `pr` and `full` entirely undocumented and does not clarify the nested object shape beyond a terse sketch.

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 implies a completion/marking-action ('Done means live', evidence gating, refusal), but never states plainly that it marks a task complete or names the task resource explicitly. The agent must infer the core verb+resource from the tool name rather than the text. It is distinct enough in spirit from siblings like pause_task, but the purpose is conveyed obliquely.

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?

It gives substantial conditional routing: full completion requires `evidence` for every criterion or is refused; incomplete work uses `partial: true` + `remains`; `review: true` routes to PR review. It also states the push/test preconditions and the `force: true` escape hatch. It stops short of naming sibling alternatives, so it is clear context without explicit exclusions.

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