govcon-feed

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

The description fully carries the burden due to no annotations. It explicitly states the data recency (last 180 days), types of events returned (win/lose/modify), and that events accrue over time. This is good transparency, though it omits potential limitations like pagination or number of results.

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, well-structured sentence that conveys all necessary information without extraneous words. It is front-loaded and efficient.

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?

For a tool with one parameter and no output schema, the description covers the main functionality and data scope (180 days, events). It does not describe the return structure, but the context is sufficient for an agent to understand the tool's purpose and when to use it.

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 'contractor' is described as 'contractor name' in the description, adding context beyond the bare string type in the schema. However, it does not specify expected format (e.g., exact name, partial match), which could leave ambiguity.

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 takes a contractor name and returns recent federal awards and win/lose/modify events. It specifies the time window (last 180 days) and event types, distinguishing it from sibling tools like search_awards (general search) and delta_digest (diffs).

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 implicitly suggests use for monitoring a specific contractor's activity, but it lacks explicit guidance on when to use this tool versus alternatives (e.g., search_awards for broader queries). No when-not-to-use or exclusion criteria 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 are provided, so the description carries full burden. It does not disclose whether the tool is read-only, destructive, or any side effects. It implies a non-modifying digest but omits response format, authentication needs, or rate limits.

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 two sentences, front-loaded with the core purpose. It is concise but could benefit from a brief summary of filtering options or output example.

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 8 parameters and no output schema, the description is insufficient. It does not explain the return format, how filters interact, or provide example usage. The tool is underdocumented for effective selection and invocation.

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 only 25% (only 'days' and 'expiringDays' have descriptions). The description adds minimal meaning beyond correlating 'expiringDays' with expiring contracts. Key parameters like 'naics', 'agency', 'keyword', 'maxAmount', 'minAmount', and 'recipient' are left entirely unexplained.

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 a weekly delta digest of new awards, modifications, and expiring contracts, with filtering. It distinguishes from sibling tools like 'search_awards' by focusing on time-bound changes and recompete opportunities.

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 indicates it is 'best signal for BD teams' and implies use for weekly monitoring. It lacks explicit when-not-to-use or comparisons with alternatives, but the purpose is clear enough for situational guidance.

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 must disclose behavioral traits. It states 'Direct live search' implying real-time external API access, but fails to mention safety (read-only), rate limits, authentication, or data freshness.

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?

Two short, front-loaded sentences with no superfluous information, achieving high information density.

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?

Despite 9 parameters and no output schema or annotations, the description omits return format, pagination details, error handling, and caveats about live external data latency.

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?

Only 11% of parameters have schema descriptions (limit); description lists categories (naics, agency, keyword, date range, $ range) but provides no format, syntax, or examples for the 9 parameters. Falls short of compensating for low schema coverage.

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 'search', resource 'US federal awards (USAspending.gov)', and lists search dimensions (NAICS, agency, keyword, etc.). It differentiates itself from sibling tools which focus on competitor watching and change detection.

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?

Says 'Use for ad-hoc lookups', giving a general usage context. However, no explicit guidance on when not to use it or alternatives, though siblings are unrelated.

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?

With no annotations, the description carries full burden. It discloses the incremental behavior and cursor usage but omits details like rate limits, pagination beyond limit, cursor expiration, or whether the operation is read-only. Transparency is adequate but not comprehensive.

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, well-structured paragraph of three sentences. It front-loads the core purpose, then explains cursor usage, then lists filters. Every sentence adds value without redundancy.

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 lacks details about the return format (e.g., whether response includes a new cursor for iteration) and does not cover pagination behavior beyond the limit parameter. Given the tool's role as a delta feed, this missing context reduces 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 63%, and the description adds value by grouping filters (NAICS, agency, etc.) and clarifying the cursor's role ('bookmark'). It explains the cursor usage pattern beyond the schema, though it does not mention the limit parameter explicitly.

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 returns 'federal contract awards that are NEW or MODIFIED since a cursor token,' identifying the specific verb ('return'), resource ('federal contract awards'), and unique incremental nature. This explicitly differentiates it from siblings like search_awards (full search) or competitor_watch (different focus).

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 the core usage ('Pass the cursor from a prior call to get only changes since then') and lists filter options, providing clear context. However, it does not explicitly compare to sibling tools or mention when not to use it, missing full exclusion guidance.

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