get_opportunity_changesGet sanitized immutable changes with separate source and detection times.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | ||
| limit | No | ||
| since | No | ||
| notice_id | Yes | ||
| materiality | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: changes are sanitized (redacted/cleaned), immutable (append-only), and carry separate source and detection times. This helps the agent understand the nature of returned data beyond basic read-only semantics.
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, front-loaded sentence that efficiently states the core purpose and distinctive features. There is no fluff or repetition; every term earns its place.
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 five parameters, no schema descriptions, and no output schema, the description is insufficient for confident tool invocation. Annotations provide safety context, but the missing parameter semantics and result structure leave significant gaps that the sparse description does not fill.
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 0%, and the description does not explain any of the five parameters. It only implies that notice_id identifies the target opportunity. The meanings of type, limit, since, and materiality are left undocumented, forcing the agent to guess at filter semantics.
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 uses a specific verb ('Get') and resource ('opportunity changes'), and further specifies unique characteristics ('sanitized immutable changes', 'separate source and detection times'). This clearly distinguishes the tool from siblings like get_opportunity, which likely returns current opportunity details, and get_opportunity_documents for files.
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 offers no explicit guidance on when to use this tool versus alternatives or scenarios where it should not be used. While 'change history' implies an audit or history use case, no comparison or exclusions are provided, leaving the agent without clear decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear boundaries (e.g., get_award vs search_awards, get_business_profile vs get_vendor). Some overlap exists in pairs like find_recompetes/find_recompetes_for_business and search_opportunities/search_opportunities_for_business, though the latter are differentiated by profile context.
All tools follow a consistent verb_noun snake_case pattern (get_, search_, update_, watch_, save_, etc.) with no stylistic deviations. Naming is highly predictable across the entire set.
At 39 tools, the surface is excessively large. While the domain is broad, many tools could be combined or parameterized (e.g., get_business_awards and get_vendor_awards, multiple search variants). This creates overhead for agents and dilutes focus.
The tool set covers the core lifecycle: opportunity/award searching and retrieval, business profile updates, saved searches, watches, exclusions, and reference data. Minor gaps such as award amendments or more granular exclusion handling exist, but the surface is fundamentally complete.