martin_dossier

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

The annotations already declare readOnlyHint and idempotentHint, so the description only needs to add context beyond that. It adds aliases and output-format behavior, but 'safe to trust' is a vague promise rather than a concrete description of what the tool does with the run data, and there is no mention of how the format options affect output or side effects.

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 contains only two sentences, is front-loaded with the alias naming, and every sentence contributes in a meaningful way. No redundant fluff is present.

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?

Although annotations and an output schema cover safety and return shape, the core invocation problem remains unsolved because the oneOf selector parameters (file, loopId, latest) and runsDir are unexplained while schema descriptions are empty. The description provides enough context for a high-level why but not enough for an agent to confidently choose the correct parameter family in every case.

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 0%, so the description must explain the parameters, and it only maps roughly to the format parameter by mentioning JSON, Markdown, and GitHub PR formatting. It does not explain how file, loopId, latest, or runsDir select the target run or control the dossier, leaving most parameters semantically opaque.

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 identifies the tool as an alias for martin_run_dossier and says it is used after martin_run to understand what happened and whether the result is safe to trust, giving a clear purpose. It also names the supported output formats, but it never spells out an operational verb like 'generate a dossier report', and it does not explicitly differentiate from close siblings such as martin_get_run or martin_pr_summary.

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?

It gives explicit workflow guidance: use after martin_run to determine what happened and whether the result is safe to trust. This tells the agent when in the process to invoke it, though it does not state when to avoid it or what to use instead for related but distinct needs like detailed run inspection or PR summary.

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