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

With no annotations, the description fully covers behavioral aspects: it is a probabilistic estimate from public data, not insider info, and outputs include base rates, sample size, and confidence band. It does not elaborate on data freshness or specific interpretation of 'honest confidence band', but overall sufficient.

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?

Three sentences, front-loaded with purpose, then input options, then output details. No superfluous text; each sentence adds essential information. Efficiency is optimal.

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?

Given 5 parameters, 100% schema coverage, no output schema, the description sufficiently covers inputs and outputs. However, it lacks mention of error handling for invalid contract IDs or edge cases. Overall, substantial but not exhaustive.

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 descriptions for all 5 parameters. The tool description adds value by explaining that 'gid is best input', that 'naics and incumbent are required if no gid', that 'agency sharpens the lane', and that topN has a default of 5 (not in schema). This clarifies usage beyond the schema.

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?

Description clearly states the tool predicts recompete winners, specifies inputs (contract ID or NAICS+incumbent pair), and lists outputs (incumbent probability, competitors, base rates, sample size, confidence band). It distinguishes from sibling tools 'expiring_recompetes' (lists contracts) and 'lane_competitors' (lists competitors) by focusing on prediction.

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?

Description provides clear input options: 'Pass a contract identifier ... OR a NAICS+incumbent pair' and indicates 'gid is best input' while 'naics and incumbent are required if no gid'. However, it does not explicitly state when not to use the tool or compare directly with siblings for decision-making.

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