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

Annotations declare destructiveHint=true and idempotentHint=false, and the description earns its place on top of them by spelling out the actual blast radius ('REPLACES the project's catalogue'), the runtime cost ('takes minutes'), the concurrency limit, and the human confirmation gate. It also discloses the return shape (a summary plus a tc_confirm code), which matters for a call that is otherwise inert.

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 verb and the destructive outcome, then facts in descending importance. Slightly undermined by the confirmation gate being stated twice ('The person confirms before it starts. Nothing happens until the person confirms'), which is redundant rather than clarifying.

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 3-parameter mutation tool with no output schema, the definition covers blast radius, duration, concurrency, confirmation flow and the next tool to call. The only omission, the return format's exact fields, is partly addressed by saying it returns a summary and a code.

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 the schema already documents mode, site and project_id. The description still reinforces the crucial mode asymmetry (preview vs destructive import) in prose, which is the single semantic an agent must not get wrong, though it says nothing extra about the site parameter.

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: crawls one of the organization's VERIFIED websites into a Search project. It clearly distinguishes itself from search_import_status (progress checking) and search_create_project, so an agent can route correctly without opening a 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?

Explicitly contrasts the two modes ('preview' reports and changes nothing vs 'import' REPLACES the catalogue) and names the follow-up sibling for progress. It also supplies the operating constraint that only one import runs at a time, leaving little to inference.

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