mark_retryable

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

No annotations, so the description carries the full burden — and it delivers: it states the trial becomes terminal, does not count as evidence, does not unlock re-capture/re-run, and references an enforcement rule (commitment 1, orphan check). This is exactly the behavioral context an agent needs before an irreversible mutation.

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?

Front-loaded with the core action and the critical when/when-not distinction, then the do-not-unlock warning, then the enforcement note. Well organized, though slightly long and the trailing enforcement sentence is a bit cryptic without more context.

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?

An output schema exists so return values need not be explained. For a mutation tool with no annotations, the description supplies everything an agent needs: what qualifies, what it excludes, the terminal/evidence semantics, the non-unlock caveat, and the correct alternative route.

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 all three parameters (programme_id, trial_id, reason). The description adds the useful detail that reason 'becomes part of the record', but no syntax or format guidance. Baseline 3 is correct when the schema does the heavy lifting.

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?

Specific verb (mark) + resource (running trial as retryable) with explicit scoping: it names the exact condition (infrastructure failure: server restart, executor state lost, timeout) and distinguishes it from scientific failures. Among siblings like correct_trial_status and cancel_trial, the retryable-vs-scientific-failure distinction lets an agent pick it correctly.

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?

Explicit when-to-use (stuck-in-running infrastructure failures) and when-not (scientific failures), plus a named alternative path: design_experiment a new trial and capture_bundle on it. It even warns that this does NOT unlock re-capture/re-run, closing the main misuse route.

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