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

Adds substantial behavioral context beyond the annotations: partial files are preserved, a NEW task_id is returned (so the caller must poll the new id), and hard retry budgets per error class (TASK_TIMEOUT/STALE_TASK twice, TASK_FAILED once). The annotation destructiveHint=true is consistent with the resume semantics described.

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 then layered with the critical caveats (new task_id, retry budget, error classes). Dense but every sentence carries load-bearing information; the em-dash list is efficient.

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 a mutation tool with an output schema already present, the description covers what an agent needs to invoke it correctly: trigger condition, side effects on existing artifacts, the returned handle change, and retry policy. Nothing material is missing.

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 both parameters (task_id, context) are already documented. The description reinforces that task_id comes from the failed create/modify task, but adds no format or syntax detail 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?

States a specific verb (resume) and a specific resource (a failed/stalled create/modify task), and distinguishes it from the sibling create_app by framing it as resumption rather than a brand-new build. An agent can tell exactly what this does without opening the schema.

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 trigger ('Use this when check_task reports failed'), the named alternative it is not ('instead of starting a brand-new create_app'), and the polling follow-up ('poll check_task on that NEW id'). Exclusion conditions are also stated for non-transient errors.

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