martin_get_verification_results

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

Annotations already cover the read-only and idempotent hints, so the description only needs to add meaningful behavioral detail. It does add that data comes from 'stored loop events and ledger entries', which is useful. It does not describe whether all evidence is returned, how missing evidence is handled, or what the output structure tends to contain.

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 definition is a single, compact sentence that communicates the action, resource, and source in one line. That is effectient. It lacks the extra routing or eligibility sentence that would make it more complete, so it doesn't earn the top 5 for structure.

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 schema and output schema cover much of the technical context, and the annotations handle safety. But the overall context is incomplete: the agent gets worn else from the description, but not when to select this tool among siblings nor how to choose between the two, not both being identified. This is a clear gap for a tool with many neighbors.

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 100%: `file`, `loopId`, and `runsDir` each have explicit descriptions, and the oneOf constraint is present. The descriptive text adds no task-level parameter guidance, but the structure does the heavy lifting here, so the baseline 3 is appropriate.

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 makes a clear statement of action and target: 'Load verification evidence for a Martin run'. The added source phrase 'from stored loop events and ledger entries' sharpens the scope and separates it from sibling tools that fetch run metadata, attempts, or status. It does not name the sibling distinction directly, so it falls short of a 5.

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 guidance on when to use this tool instead of martin_get_run, martin_get_attempt, or other siblings. There is also no hint about choosing the `file` parameter versus the `loopId` parameter, even though the schema expresses a oneOf constraint. An agent must infer usage solely from the name and schema.

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