Reconcile a review packet vs task/spec/diff

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

Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds behavioral context: the tool returns specific types of issues and does not issue a final verdict. This complements annotations without contradiction.

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 three sentences, front-loading the action and inputs, then listing outputs, and finally clarifying constraints. Every sentence adds value with no unnecessary words.

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?

With an output schema present, the description need not detail return values. It covers purpose, inputs, outputs, and behavioral constraints sufficiently for the tool's complexity, given rich annotations and schema.

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 100%, so the schema adequately describes the two parameters. The description adds minor context (e.g., task is a stem, base is a branch/commit) but does not significantly enhance understanding beyond the schema.

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 reconciles a finished run by comparing task, spec, review packet, and git diff. It lists specific outputs (coverage gaps, empty-evidence Pass rows, scope drift, self-report mismatches, human-attention list) and distinguishes itself by explicitly stating it never issues a final verdict, setting it apart from sibling tools.

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 indicates when to use ('Reconcile a finished run') and specifies that the tool does not give a final verdict, implying a human or independent reviewer should act on the output. However, it does not explicitly compare to alternatives or state when not to use.

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