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

Annotations already cover safety (readOnly, openWorld, non-idempotent), and the description adds genuinely new behavior: an ~40 second wait bound, per-check return structure, issue ordering by importance, and that each issue carries evidence plus a recommendation. With no output schema, this return-value disclosure is the main value-add; only error/failure behavior and any quota cost are left unstated.

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, no filler, with the core action and time bound front-loaded and the return contract following. The default check list is the densest part but is load-bearing information not available elsewhere.

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 4-parameter, no-output-schema tool with read-only annotations, the description supplies latency expectations, return shape, prioritization, and the handoff to sibling tools. What is missing is marginal but real: what happens on timeout or failed checks, and whether repeated runs consume quota (relevant given a 'usage' sibling exists).

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 baseline is 3; the description earns above baseline by enumerating the actual default check ids (meta-tags, page-structure, ai-crawler-access, redirects-headers, entity-schema), which the schema only alludes to as 'the quick default set'. It does not add meaning for url, mode, or fresh beyond what their schema descriptions already say.

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 ('Runs BACKLNK checks on one public URL'), names the scope constraint (single public URL), and implicitly separates itself from get_report/verify_fixes by noting it only produces audit ids for them. An agent can distinguish this from list_checks and get_report 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?

Clear context is given: this is the entry point that produces audit ids consumed by get_report and verify_fixes, and it explains the default check set when 'checks' is omitted. It lacks explicit exclusions (e.g. when to prefer verify_fixes over a re-run, or when to set fresh=true vs relying on cache), so it stops short of a full when/when-not map.

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