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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds genuinely non-obvious behavior: PII and free-text fields are stripped at ingest, filters AND together, q is a full-text search across all fields. It also discloses the credit cost per call and the anonymous rate limit (5-row preview, 20 calls/day), which annotations cannot express.

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 what the dataset is, then data-hygiene, then filter/cost semantics — every sentence carries information. It is dense and packs filter semantics and pricing into mid-sentence clauses, but nothing is redundant.

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?

Coverage, privacy behavior, and pricing are well handled, and there is no output schema to explain. But for a 15-parameter tool with zero schema documentation and no output schema, an agent still cannot tell how to build a targeted query (which identifier field, which date pair, what classification values are valid).

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?

With 15 parameters at 0% schema description coverage, the description must carry the load, yet it only explains two of them ('q searches all text fields', 'Filters combine with AND'). It says nothing about the distinction between excluding_agency and excluding_agency_name, the exclusion_type/classification/classification enums, uei_sam vs cage_code, activation vs termination date bounds, or page/per_page pagination limits.

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 and scope: 'Every active exclusion (debarment) on the official US SAM.gov list', enumerating entity types (individuals, firms, special entities, vessels) and the fields returned (agency, program, dates). This clearly distinguishes it from siblings like query_uk_sanctions or query_eu_ted without opening a 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?

Usage is implied through 'normalized for supplier due diligence' and 'for compliance purposes', which frames the screening use case. However, it never says when to prefer this over query_uk_sanctions or the other screening tools, and gives no exclusions or prerequisites for the caller to weigh.

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