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

The existing annotations (readOnlyHint, idempotentHint, destructiveHint) already signal a safe, non-destructive operation. The description adds substantial behavioral detail beyond that: 'Keyless' indicates no authentication, 'queried live' means the data is fetched in real time, and the corpus size ('~37,000 notices') sets expectations; it also reveals the default 'open-only' sort ('sorted soonest-first'). These are behavioral traits not otherwise captured by the annotation structure.

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?

The description is two sentences that pack distinct information without redundancy: the first covers the resource and notice types, the second covers filters, defaults, and sorting. The third sentence adds the result shape and operational characteristics. Every sentence contributes to tool selection or invocation; no filler material is present.

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?

Although there is no output schema, the description explicitly states what each result carries ('the notice id, project, deadline, and a document URL'), which is adequate return-value guidance. The 6 optional parameters are fully documented in the schema, annotations cover safety/idempotency, and the description addresses operational details (keyless, live, scale) that an agent would need. For a read-only search tool, this is complete.

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?

The input schema has 100% description coverage and already documents each parameter's allowed values, default, and matching behavior (e.g., 'partial/case-insensitive match', 'default 15', 'open_only'). The description only aggregates the filter names ('country, sector, keyword') and gives the open_only default without adding any new parameter-level semantics. With the schema doing the heavy lifting, a baseline of 3 is correct.

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 opens with a specific verb+resource: 'Search Inter-American Development Bank (IDB) project procurement notices', then enumerates the exact notice types ('live bidding notices, expressions of interest, general/specific procurement notices, and contract-award notifications'). It also scopes the geographic coverage ('26 Latin American and timezone-leading countries') and the default derived behaviors (open-only, soonest-first), which distinguishes it from siblings like idb_get_notice and idb_search_awards.

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 description gives a clear usage context: it identifies the resource and the available filters ('Filter by country, sector, and keyword'), the default for open_only, and the sort order. However, it does not explicitly mention alternatives such as idb_get_notice or idb_search_awards, or state when not to use this tool. The 'keyless, ~37,000 notices' line implies a broad use case, but no firsthand comparisons are made, so a 4 is appropriate.

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