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

Annotations cover only the safety profile (readOnly, non-destructive, open-world); the description adds the traits an agent actually needs to avoid failure: per-network-address rate limits, the x402/0.01 USDC payment path, the 5 vs 25 result cap, the fact that empty searches still consume quota, and recovery via identical arguments plus the original proof. That is well beyond what the structured fields provide.

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?

Five compact sentences with the purpose front-loaded and the quota/payment constraints immediately after. Every clause carries actionable information (matching rule, quota, payment, edge case, retry), and the terse "Empty searches count" warning earns its place by pre-empting a quota surprise.

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?

The operational and commercial behavior is documented thoroughly and no output schema is needed for return values, so the description is complete on the 'how to call it safely' axis. It is incomplete on the 'what the arguments mean' axis for a 9-parameter tool, where cryptic fields like snapshot and deadline ranges remain unexplained.

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 0% across 9 parameters, so the description carries the full burden and only partially compensates: it clarifies q's matching semantics, that region means work location rather than buyer address, and limit's cap tiers. cpv, status, snapshot, offset, and especially the deadline_from/deadline_to formats get no explanation anywhere, leaving two-thirds of the surface undocumented.

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 ("Search the latest ingested UK Find a Tender notices") and scopes it to ingested notices, which cleanly separates it from get_tender_details and check_coverage. It also pins down matching semantics ("Literal AND keywords"), so an agent knows what kind of search this is without opening the 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?

Gives strong operational context: the free-call allowance, when payment kicks in, result-count tiers, and retry behavior after an uncertain payment. It does not, however, name the sibling tools or say when to prefer get_tender_details / check_coverage over a fresh search, so routing between siblings is left to inference.

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