inspect_evidenceInspect the provenance behind startup credits and deals. Resolve one to ten exact revisions to supporting events and observations, including freshness and dispute status.
| Name | Required | Description | Default |
|---|---|---|---|
| revision_digests | Yes | Exact offer revision digests returned by Sourcey search or comparison. |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| release_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering safety well. The description adds 'freshness and dispute status' as behavioral context, which is meaningful. However, it doesn't disclose what happens with invalid digests or disconnected revisions.
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 sentences, front-loaded purpose, concise. The 'one to ten' and 'exact revisions' details are useful and add specificity without waste. No redundancy with annotations.
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 an output schema (which handles return-value documentation), full annotation coverage, and 100% schema description coverage. Given this strong structured foundation, the description reasonably covers purpose and key behaviors. 'Freshness and dispute status' hints at output richness. Adequate but not exceptional.
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 the schema fully documents revision_digests. The description adds 'exact revisions' and 'returned by Sourcey search or comparison' context, which clarifies the subtype of digests (offer revisions vs arbitrary hashes). Baseline 3 with modest added value.
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 states 'Inspect the provenance behind startup credits and deals' which has a clear verb+resource. However, it doesn't distinguish this from siblings like compare_offers or get_changes. 'Resolve one to ten exact revisions to supporting events and observations' clarifies scope but the differentiation from get_changes is ambiguous.
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 mentions resolving 'exact revisions' returned by 'Sourcey search or comparison,' partially implying input prerequisite. However, there's no explicit when-to-use vs. alternatives guidance for compare_offers or get_changes, nor exclusions for when NOT to use this tool.
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.
Each tool addresses a distinct concern: searching, comparing, tracking changes, inspecting evidence, and preparing declarations. There is no functional overlap that could cause an agent to select the wrong tool.
All tool names follow the consistent verb_noun pattern (compare_offers, get_changes, inspect_evidence, prepare_declaration, search_offers) using lowercase with underscores, forming a predictable and uniform convention.
With 5 tools, the server is well-scoped for its domain of startup deals and credits. Each tool serves a necessary role, and the count is neither too sparse nor bloated.
The tool surface covers core workflows: discovery, comparison, change tracking, and evidence inspection. A minor gap is the lack of a direct 'get one offer by ID' tool, but search_offers can serve that purpose, so agents can achieve results without major dead ends.