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

Goes well beyond the annotations by disclosing rate limits (three an hour, ten a day per address), that a human replies to email, that the reply carries a reference id, and that one call suffices. These are operational facts an agent cannot infer from destructiveHint=false / idempotentHint=false.

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?

Purpose is front-loaded in the first clause, then constraints, then the kind taxonomy. Dense parenthetical shorthand ('waitlist (product letme, only email needed)') is efficient but slightly cryptic. No sentences are purely filler.

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 8 parameters, no output schema, and a mutation-style tool, the description covers the essentials: what is sent, where it goes, throughput limits, and what comes back. It omits which optional parameters matter per kind, though the schema descriptions cover that gap.

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% and the enum descriptions already spell out every kind, so the description's kind list largely restates structured data. It adds only marginal detail, such as 'waitlist (product letme, only email needed)', which is also in the schema. Baseline 3 is the right call when the schema carries the load.

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 recipient ('Sends a message to the Anchor Terminal team') and clarifies the channel is the same one the site's forms use, with a human replying by email. An agent can tell it is a contact-form tool. It does not distinguish itself from the sibling file_issue, which is the one adjacent tool an agent might confuse it with.

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 only when your user asks you to get in touch' is an explicit inclusion rule plus an exclusion, rare in this dataset. The per-kind mapping (listing needs url, claim/dispute concerns a listing, waitlist needs only email) gives concrete routing guidance for each use case.

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