get_evidenceRetrieves a document's proof package: SHA-256 hashes of original and signed PDFs, signer events with their hash-chain positions, and steps to verify it independently.
The evidence package for a document: SHA-256 of the original and signed PDFs, every signer and event with its position in Signathing's public hash-chained evidence log, and the recipe to verify it independently.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose substantive behavioral content: exactly which artifacts come back (SHA-256 of original and signed PDFs, signer/event records, positions in a public hash-chained log) and that an independent verification recipe is included. It stops short of stating the safety profile (read-only, no side effects) or any auth/rate-limit requirements.
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?
A single dense sentence that front-loads the resource and then enumerates contents in a scannable list; no filler or repetition.
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 no output schema, the description usefully doubles as return-value documentation, telling the agent what the evidence package comprises. It leaves minor gaps — the meaning/format of id, error behavior for unknown documents — but is otherwise complete for a simple read getter.
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?
There is one parameter (id) at 0% schema description coverage, so the description is the only place meaning can come from. The phrase 'for a document' implies id is the document identifier, which is genuine added context, but the description never documents the parameter explicitly or its accepted form.
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 names the resource (evidence package for a document) and itemizes its contents — hashes, signers, events, log positions, verification recipe — so an agent knows exactly what it fetches. It lacks an explicit verb ('retrieves') and never names the nearby sibling get_document or verify_signature_code, which would have sharpened differentiation.
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?
There is no when-to-use guidance, no exclusions, and no reference to the sibling tools an agent might confuse this with (get_document for the document itself, verify_signature_code for a single code). The agent must infer that this is the audit/forensic route rather than the general document route.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.