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

Annotations declare a non-read-only, non-destructive write; the description adds genuinely non-derivable context: a human at Kula Labs reads it, no agent id is retained, notes are deleted after 90 days, and personal data must not be sent. That privacy/retention and human-review detail is exactly what structured fields cannot convey. It stops short of saying whether the submission is acknowledged or what happens on error.

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?

Roughly five compact sentences, with the incentive ('Free, no key') and the call to action front-loaded, followed by privacy and retention caveats. Every sentence carries information; nothing is obviously padded.

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 no output schema and 7 parameters, the description covers purpose, the human-review loop, data retention, and a personal-data warning — enough to call it correctly. The remaining gaps (enum meanings, listing_id's role beyond the schema note) are handled by the input schema itself.

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 57%, so the schema carries most parameter meaning and the baseline is 3. The description maps to three fields (looked_for, found_it, missing) but does not explain the 'reason' enum, currency, listing_id, or would_pay_minor, leaving those entirely to 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 states a concrete action — submit a one-sentence note describing what you looked for, whether you found it, and what was missing — going beyond the bare name. It is distinguishable from siblings like ask_market or search_listings, though it never explicitly names an alternative. The 'Free, no key' opener front-loads the key differentiator for an agent deciding whether to bother.

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 trigger is stated directly: 'Leaving, or did not find it? Tell us...', which tells the agent this is the fallback after an unsuccessful search. It gives clear context for when to invoke it, but names no explicit when-not conditions and no alternative tools to prefer instead.

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