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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world. Beyond those, the description discloses meaningful behavior: results are ordered verified → claimed → listed, and POS count may be NULL. That adds value the annotations don't cover.

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 the resource and the prerequisite lands last, which is reasonable. However, the long parenthetical enumerating return fields is largely redundant given an output schema exists, and its mid-sentence interpuncts read awkwardly for an agent parsing quickly.

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?

Annotations cover the safety profile and an output schema covers returns, so the description's main remaining duties are param meaning and prerequisites. It delivers the decision_id gating context but misses limit/query semantics, leaving the six-parameter surface only partially explained.

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 0%, so the description must carry parameter meaning. It covers market ('for this market'), decision_id, and the channel/department filters, but says nothing about limit or query — two of six params remain undocumented anywhere.

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 resource — retail buyer desks for a market — and enumerates the banner-record fields it returns (banner, parent group, channel, format, POS count, buyer desk). This distinguishes it from the supplier-side sibling, but the dense parenthetical makes the core verb ('find') less immediately legible.

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?

Provides a real prerequisite — it takes the decision_id of an allow decision, implying a prior gating step — and names the available filters (channel, department). It does not, however, contrast with alternatives like find_verified_supplier or state when not to use it.

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