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

Annotations only say readOnly/openWorld; the description adds real meaning per state (verdict, human approvals, healed version on completion) and discloses that some runs block on human approval. Also documents that wait_seconds enables long-polling rather than returning immediately. Missing guidance on what happens at the 110s cap or how expired/declined differ operationally.

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 purpose, then state semantics, then the polling knob. Dense but nearly every clause carries information; the parenthetical about local server deployment is slightly tangential but still routing-relevant.

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?

For a 2-param read-only status tool with no output schema, it covers all states, the blocking case, and the long-poll behavior. An agent could poll correctly after reading this, though timing/backoff expectations at the 110s ceiling remain implicit.

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 coverage is 100%, so run_id and wait_seconds are already documented in-schema, including the default of 30 and the 0-110 range. The description only reinforces wait_seconds as a long-poll knob, adding marginal meaning beyond the schema. Baseline 3 applies.

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+resource (check status of a run) with the full enumeration of possible states spelled out. It also distinguishes itself from siblings by naming try_skill as the starter and noting run_skill lives on a different (local) server.

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?

Gives concrete conditional guidance for the tricky state: on pending_approval, tell the user and wait. It also clarifies which endpoint starts runs (try_skill, capped public replay) versus run_skill on the local server. Lacks an explicit statement of when not to poll or a timeout/expiry cadence.

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