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

Annotations already cover readOnly, idempotent, and non-destructive behavior, lowering the burden. The description adds meaningful traits: sanctions hits zero the score regardless of other signals, and the output reports sources that failed, which sets expectations about partial failures and the override rule.

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 dense but efficient: core action and scale first, then data sources, then explicit return values, then the critical zeroing rule and usage trigger. Every sentence earns its place and there is no repetition of schema or annotation metadata.

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?

With no output schema, the description fully enumerates the return payload: score, risk band, itemized evidence with citations, queried/failed sources, and a plain-text summary. Combined with a single well-documented parameter and rich annotations, an agent has all needed information to select and invoke this tool correctly.

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%, with the sole parameter company_name already documented with examples and a normalization note. The description adds no additional parameter-level semantics, so the baseline of 3 is appropriate.

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 verb and resource: 'Compute a composite 0-100 Counterparty Risk Score for a company name.' It enumerates the exact data sources combined and the return contract (score, band, evidence, sources queried/failed, summary), so an agent can distinguish it from other risk scorers without guessing.

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 an explicit trigger: 'Use this when you need a single-call counterparty risk verdict instead of stitching five separate queries.' It tells the agent when this tool is the right convenience choice, though it does not name specific sibling alternatives like company_trust_check or entity_dossier for exclusion.

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