memory_fetch_evidence

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds a behavioral detail about verifying the 'exact candidate hash', which hints at a validation operation. However, it does not disclose what happens on mismatch, the meaning of 'registered', or any error behavior, so the added transparency is limited beyond annotations.

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 concise sentence with no fluff, front-loading the core action 'Fetch registered evidence'. It earns its place by stating both the primary action and the verification behavior. However, it is terse to the point of under-specification given the tool's 7-parameter complexity, so it doesn't reach a perfect conciseness score.

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 7 parameters, zero schema descriptions, and no output schema content provided, the description is vastly incomplete for correct invocation. It does not explain domain concepts, parameter relationships, or the verification process, nor does it differentiate from nearby memory tools. The existence of an output schema does not compensate for the missing input semantics and usage context.

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 schema has 7 parameters and 0% description coverage, placing the full burden on the description. The description only hints at 'candidate hash' (likely expected_sha256) and 'registered evidence' (path/line), but fails to explain path, start_line, end_line, event_id, context_lines, or allow_mismatched_content. This is severely inadequate for an agent to correctly construct a valid invocation.

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 specific verbs 'Fetch' and 'verify', and names the resource 'registered evidence' and 'candidate hash'. It distinguishes itself from sibling tools like memory_search_candidates (searching) and memory_latest (recency) by focusing on fetching a specific evidence record. However, 'registered evidence' is a domain-specific term that isn't defined, and the verification aspect is somewhat vague, preventing a perfect score.

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 provides no explicit guidance on when to use this tool versus alternatives. It implies usage for retrieving evidence and optionally verifying a hash, but does not state exclusions, prerequisites, or mention sibling tools like memory_search_candidates or memory_check_evidence_eligibility. The absence of contextual cues leaves the agent to infer the appropriate scenario.

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