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

Goes well past the annotations: it discloses that the checks are 'fixed rules, not a model', defines the three states and what triggers parking, notes that parking notifies no one, and gives concrete rate limits (120/min per address, 600 with a key, shared across all MCP calls, retry_after on error). It doesn't state what the findings payload looks like, though an output schema exists, so the gap is minor.

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-loaded with purpose, then routing, then behaviour, then inputs — a sensible order with almost no filler. It is dense and runs long as a single prose block, with a few self-contained asides (the parenthetical on reaching a person, 'listed once you send a key') that could be trimmed or bulleted for scanability.

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?

The tool has nested params, enum'd directives, four annotations, and an output schema, and the description covers everything an agent still needs: prerequisites, state semantics, rate limits, and the answering conventions. Nothing required to call it correctly is left to inference.

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 already 100%, but the description still adds semantics the schema lacks: answers are keyed by must_answer id including directive-N for each Directive in tension, each needs at least 15 characters of real content, human_knowledge may honestly be 'nothing relevant', 'does not apply, because...' counts as addressing a Directive, and needs_human='yes' deliberately parks. The one omission is that it doesn't explain why question/directives must match frame_deliberation's input other than 'a different set of Directives is checked'.

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 — 'Audit the shape of a finished deliberation' — and immediately scopes it ('It checks shape, never whether you are right'). It explicitly distinguishes itself from the three closest siblings: frame_deliberation (prerequisite), attest_deliberation (same findings, signed into a token), and ask_guidance (single planned action, no conflict).

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?

'Use it after frame_deliberation and before you act' gives an unambiguous ordering, and the alternatives are named with the condition that selects each: attest_deliberation for a token, ask_guidance for one planned action with no conflict, deliberate_open to actually reach a person. When-to-use and when-to-use-something-else are both covered.

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