govcon-recompete

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

The description is transparent about the tool's read-only nature and its function of listing contracts with predictions. It adds context about the horizon window (period-of-performance end) but does not discuss side effects or limitations, which is acceptable for a non-destructive tool.

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 concise: two sentences that front-load the main action and then contextualize the tool as the recompete pipeline feed. No unnecessary words.

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 enough context given the tool's complexity: it states the output (list with predictions) and notes filtering. It does not detail return fields, but no output schema exists, so this is reasonable.

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 83% schema coverage, the description adds minimal extra meaning beyond the parameter descriptions. It explains that minDays/maxDays define a horizon window and that filters are by NAICS and agency, but this largely repeats 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?

The description clearly states the tool lists federal contracts expiring in a defined horizon window, includes winner predictions, and allows filtering by NAICS and agency. It distinguishes itself from siblings by calling itself the 'recompete pipeline feed,' which differs from lane_competitors and predict_recompete.

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 implies usage (for seeing upcoming recompetes) but does not explicitly mention when to use this tool over alternatives like lane_competitors or predict_recompete. No exclusions or prerequisites are provided.

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

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

No annotations provided, so description carries full burden. It mentions ranking by recent wins and dollars but does not disclose calculation details, data freshness, or any destructive behavior. Adds some context but lacks depth.

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?

Description is a single sentence that efficiently conveys purpose and ranking criteria. Slightly dense due to dash structure, but overall concise and front-loaded.

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?

Tool has 3 parameters and no output schema. Description explains purpose and ranking but omits return structure, pagination, or error handling. Adequate but not fully complete for complex usage.

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 description coverage is low (33%). Description adds meaning to 'naics' and 'agency' parameters by explaining their roles, but does not specify format or constraints like case sensitivity or accepted values.

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 verb 'Return', resource 'firms', and provides context about ranking by award velocity in a NAICS lane. Distinguishes from sibling tools by focusing on likely bidders for a recompete.

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 implies usage for identifying potential bidders on recompetes, with optional agency filter. Does not explicitly state when not to use or alternatives, but sibling tool names give some context.

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

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

No annotations are provided, so the description bears full responsibility. It transparently states that the estimate is probabilistic, uses public USAspending data, and is not insider info. It also mentions returning 'honest confidence band'. However, it does not disclose potential data lag or rate limits, which would improve transparency.

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 a single, information-dense sentence that front-loads the purpose. It efficiently covers inputs, outputs, and data source without unnecessary words. Slightly long but well-structured for clarity.

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 the moderate complexity and absence of output schema, the description adequately explains what the tool returns (incumbent probability, top competitors, base rates, sample size, confidence band). It covers the core functionality but could mention any limitations or edge cases for full completeness.

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%, so baseline is 3. The description adds significant value beyond schema descriptions by explaining the role of each parameter: gid as best input, naics/incumbent as alternatives, agency as optional lane sharpener, and topN default. This helps the agent understand parameter relationships.

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 predicts who will win an expiring federal contract recompete, specifies inputs (contract identifier or NAICS+incumbent), and lists outputs (incumbent probability, top competitors, base rates, sample size, confidence band). It distinguishes from siblings by focusing on prediction rather than listing expiring competitions or lane competitors.

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 when to use the tool (to predict recompete winner) and provides two clear input pathways with guidance (gid as 'best input', naics+incumbent required if no gid). It does not explicitly state when not to use it or directly contrast with sibling tools, but the context is sufficient for an agent to choose appropriately.

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