martin_get_attempt

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

The annotations already declare readOnlyHint=true and idempotentHint=true, which cover the operation's safety profile. The description's 'Load' verb aligns with these annotations and adds the detail that the result is an attempt summary with artifact directory references. However, it does not go beyond the annotations to describe other behavioral traits, so a mid score is appropriate.

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 one tightly-worded sentence with no filler. The verb and object are front-loaded, and the reference to artifact directory references is useful signal. Every phrase 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?

The presence of a full output schema, complete parameter schema coverage, and read-only/idempotent annotations means the agent does not need much more to invoke the tool correctly. The description adds the 'canonical run' context, though that term is not explained and sibling differentiation is left implicit, so it is not a perfect 5.

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%, so the schema already documents file, loopId, runsDir, and attemptIndex, including their roles in the oneOf selection. The description does not add parameter-level meaning beyond saying the artifact references are included, which is acceptable given the baseline of 3 for full schema coverage.

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 a clear verb ('Load'), a specific resource ('one Martin attempt summary'), and the key content ('artifact directory references'). It is somewhat differentiated from sibling names by the word 'attempt', but it does not explicitly contrast with martin_get_run or other related tools, so it stops 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 versus alternatives. Given the large sibling list, especially martin_get_run and martin_inspect, the description lacks explicit conditions, exclusions, or references to other tools. The only hint is the phrase 'for a canonical run', which is too implicit to count as real usage guidance.

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