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

Goes well beyond the annotations: it discloses error codes and recovery paths (400 UNKNOWN_CATEGORY with table and recommended_next_call, 400 CATEGORY_AMBIGUOUS, alias auto-correction), zero-result diagnostics (per_keyword_hits), and term-shape enforcement (≤40 chars, emails/URLs/phones rejected). It also discloses the only side effect — an append-only demand-signal write tied to the account, with no order/funds/PII — which pre-empts a naive reading of readOnlyHint=true and bounds it explicitly rather than leaving the agent to guess.

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 and scope, then organized under a MATCHING/DISCLOSURE structure so an agent can scan to the section it needs. It is dense but nearly every clause carries an actionable rule; the one cost is telegraphic phrasing that requires careful reading rather than skimming.

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?

No output schema exists, and the description partially compensates by naming response fields (matched_by:anchor, per_keyword_hits, category_resolved) and stating that results are discovery candidates, never exact. It stops short of describing the overall result shape, result caps, or pagination, which is the remaining gap for a discovery tool with no output 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 baseline is 3; the description still adds real semantics on top of the schema — category is equality-matched against a registry key with alias auto-correction, keywords are substring matches against TITLES with @anchor resolution, and keyword_match's 'all' default is tied to the synonym failure mode. What it does not add is a numeric cap rationale for 'any' or default handling for the optional filters.

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?

Names a specific verb and resource ('Buyer discovery over ACTIVE WebAZ listings') and immediately bounds the scope ('safe scope buyer_discover; OAuth grant'). It explicitly names the sibling it is not ('Exact title/SKU/URL → webaz_search'), so an agent can route between discover and search without opening either schema.

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?

States when to use it (structured intent via category and/or keywords, with optional filters) and when not to ('NOT free chat text', exact SKU/URL goes to webaz_search). It also names the conjunctive/synonym trap and the remedy ('synonyms MUST use "any"'), which is precisely the kind of usage rule an agent would otherwise get wrong.

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