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

Goes well beyond annotations by disclosing that it spends AI credits, runs asynchronously in the background, that `force` costs full price again, and that it can be refused with a named error code. Annotations only flag readOnly=false and idempotent=false; the description supplies the cost, async, and failure behavior.

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-loads purpose, then layers cost/async, force semantics, and failure mode in a tight sequence. Dense but every clause carries operational information an agent needs.

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?

With no output schema, the description correctly explains where the result appears (get_analysis) rather than in the reply. It covers cost, async execution, the force flag, and the refusal path, leaving nothing needed to invoke it correctly.

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 50%: project_id is documented in the schema, but `force` only has a title and default. The description compensates by explaining what `force` does ('re-summarizes blocks that already have a summary, at full cost'), adding meaning the schema omits.

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 ('Summarize open-text answers with AI') and clearly distinguishes the trigger action from its sibling get_analysis, which reads the result. An agent can tell this is the action that initiates analysis versus the one that fetches it.

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?

Explicitly routes the agent: 'read the result with get_analysis, do not expect it in this reply.' Names the alternative tool and the condition for each. Also states the refusal condition (text_analysis_off) and how to diagnose it via get_analysis.

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