Send Supervisory Feedback to Same OMP Session

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

Annotations already provide destructiveHint=true and openWorldHint=true, so the agent knows this tool mutates state. The description adds that it is 'bounded to remaining attempts within max_attempts', which is useful context about limits. However, it does not explain what gets destroyed (e.g., previous feedback? session progress?), nor does it clarify side effects or authorization needs. This adds some value but is not comprehensive.

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 consists of two concise sentences. The first sentence front-loads the primary verb and resource, and the second adds a critical constraint. No redundant or irrelevant information is present. Every word 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?

Given that annotations and an output schema exist, the description covers the essential purpose and a key constraint. However, it does not mention prerequisites (e.g., the session must exist and be in a state that allows continuation) or what happens if remaining attempts are exceeded. For a tool that modifies state (destructiveHint=true), a note on reversibility or confirmation would improve completeness, but the description is nearly adequate.

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 only 33% (only the `feedback` parameter has a description in schema). The tool description clarifies that `job_id` identifies the session to resume, which adds meaning beyond the schema (which only has minLength). However, `timeout_minutes` is not mentioned in either the schema or the description, leaving its purpose implicit. The description partially compensates for low coverage but leaves a gap for one parameter.

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 clearly states the tool resumes an OMP session with targeted feedback to correct defects, avoiding starting fresh. The verb 'Resume' and resource 'same OMP session' are specific, and the phrase 'bounded to remaining attempts within max_attempts' adds scope. This differentiates from siblings like omp_run_compact (which starts new tasks) and omp_cancel (which ends sessions).

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 explains the use case (correcting acceptance defects without starting fresh) and mentions a bounded constraint (remaining attempts). However, it does not explicitly state when NOT to use this tool or name alternatives (e.g., 'Use omp_run_compact for new tasks' or 'If the session has no remaining attempts, use omp_delegate instead'). The usage is implied but lacks direct exclusions.

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