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

Annotations already disclose destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description adds the critical behavioral trait that the body cannot be constructed in advance — it must be derived from two prior query_contexts calls and matching the discovered schema exactly — which is real operational context not present in the annotations. It does not say what an action creates or whether repeated calls duplicate work, so it stops short of full disclosure.

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 workflow position, then the hard prerequisite, then the action catalog. The six-item bullet list of crawler actions is slightly long but each entry helps an agent pick an action, so it earns its place; formatting with numbered steps is easy to scan.

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?

An output schema exists, so return values need not be explained. Given a single opaque nested body parameter, the description supplies the workflow position, the discovery mechanism to fill the body, and example actions — enough for correct invocation. Missing only failure behavior and side-effect specifics for a destructive, open-world call.

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?

There is a single free-form 'body' object with 0% schema description coverage, so the description must compensate. It does so by redirecting the agent to query_contexts request='actions_details' for the body structure and by naming common action types, which is meaningfully better than the empty schema — but the actual field semantics of the body remain entirely external to this description.

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 names a specific verb and resource ('Execute Company Enrichment actions') and situates it as 'Step 3 (FINAL) of workflow', which disambiguates it from siblings promots_menu/query_contexts/query_data that handle discovery and reading. The generic tool name 'execute_action' is rescued by the description, though sibling differentiation comes only implicitly via the prerequisite chain.

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 states required prior steps, names the exact tool (query_contexts) and request values ('accounts', 'actions_details') needed to build the call, and warns against guessing the body. It also lists common action identifiers so an agent can anticipate the available choices, and nothing about when-versus-what is left to inference.

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