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

The description adds behavioral details beyond annotations by stating it 'reads only an already completed cached or persisted snapshot' and 'never triggers collection or engine recomputation,' consistent with the readOnly and idempotent flags. It also notes that freshness is re-evaluated at response time, which is useful context and does not contradict annotations.

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 somewhat verbose and repetitive, starting with 'Granular, descriptive' and 'already assembled' before listing many items. It is structured into sentences about usage, returns, and behavior, but could be tightened to reduce redundancy without losing essential information.

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 description provides a broad overview of the data covered (e.g., policy corridor, repo segments) and mentions return characteristics like 'exact alignment' and 'caveats,' but lacks specificity about the output structure. Given there is no output schema, the description could be more explicit about the response format.

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 single parameter 'section' is well documented in the schema with an enum and a default description. The tool description reinforces this by mentioning options like 'compact summary,' 'one named desk section,' 'sources,' and 'all context,' aligning with the enum values. Overall, the parameter's meaning and options are clear.

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 clearly states the tool provides 'USD money-market context' and enumerates specific components like policy corridor, SOFR/TGCR/BGCR, and CP-Treasury spreads. It distinguishes from sibling tools by focusing on money market data, though the phrasing is somewhat jargon-heavy and not an explicit verb like 'get'.

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 explains how to use the 'section' parameter but provides no explicit guidance on when to choose this tool over alternatives. It mentions reading from a cached snapshot, which implies a use case for quick retrieval, but does not state conditions for preferring this tool.

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