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

All four annotation hints are false, so the description carries most of the behavioral disclosure burden. It does add real behavioral context: filing requires proof (an auth-style prerequisite) and the tool exposes both a read path (GET) and a write path (POST). However, it never says what happens on invalid proof, whether POST mutates state beyond creating an appeal, or what 'never narrows' concretely means — leaving the safety and effect profile largely unspecified.

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?

At roughly a dozen words, the description is compact and front-loads the HTTP access pattern; there is no bloat in the first and last sentences. However, 'This door never narrows' is cryptic metaphorical filler that does not earn its place and could mislead an agent rather than inform it. A clear one-line purpose statement would be far more valuable than that sentence.

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 tool with five optional parameters, dual GET/POST semantics, and an auth-sensitive token parameter (leave_token), the description leaves critical gaps: what the tool accomplishes, when GET versus POST should be used, and whether a minimal GET call is permitted without proof. An output schema exists, so return values need not be explained, but the missing purpose and selection context mean an agent cannot confidently choose and invoke this tool. The rich schema partially compensates, yet the description itself under-specifies.

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 80%, so the schema already documents nonce, leave_token, controller_signature, and controller_public_key in detailed terms, including leave_token's auth-slot semantics and the rejection of foreign tokens. The description adds only the general 'Proof required to file' notion and signals that body is the POST payload, which lightly compensates for the one undocumented param. Baseline 3 is appropriate since the schema does the heavy lifting.

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 never states what the tool actually does — no semantic verb like 'submit' or 'check' — only the transport details 'GET /api/appeal or POST {body}' and the cryptic claim 'This door never narrows.' The endpoint path merely restates the tool name, and 'Proof required to file' implies filing an appeal without saying what an appeal is, what a successful call accomplishes, or what GET returns. This is close to a tautology with HTTP details appended.

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?

There is no when-to-use guidance and no mention of alternatives; among roughly 40 siblings, tools like explain_refusal, return, and leave are plausibly related (a gate/refusal domain), yet none are referenced. 'This door never narrows' is too cryptic to function as a usable rule such as 'use whenever a refusal is issued.' An agent cannot determine when appeal is the right tool from this text.

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