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

Annotations declare non-read-only and non-idempotent, and the description adds the key side effect beyond that: the call resumes the job, so the agent knows it is a state-advancing mutation rather than a pure write of a field. It also implies a human-in-the-loop requirement ('Ask the user') that annotations cannot express. It doesn't say what happens on an invalid answer or whether resumption is immediate.

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?

Two sentences, front-loaded with the status precondition and the resume behavior, then the answer-format guidance. Efficient and readable, with only minor overlap between the description's answer guidance and the schema's own text.

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 two-parameter mutation tool with no output schema and full schema coverage, the description covers trigger, effect, and answer format. The main residual gap is failure/edge behavior (invalid option, job no longer waiting), which an agent would want before calling.

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 both job_id and answer are already documented. The description's 'one of the offered options ... or their own words' roughly duplicates the schema's 'option's label or free text' rather than extending it (no guidance on label matching, case, or ambiguity). Baseline 3 is appropriate.

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 and resource — answers the pending question of a job in needs_input status and resumes it — and gives concrete examples of the question types (which part, which architecture). No sibling tool overlaps this role, so the agent can identify it immediately.

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?

Names the triggering precondition (status needs_input) and tells the agent to ask the user before calling, plus how to shape the answer when options exist vs. free text. It stops short of stating what to do instead when the job is not in needs_input (e.g., call get_job first), so it's clear context without explicit exclusions.

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