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

The description asserts "Free read," which directly contradicts the destructiveHint=true annotation on a tool that only lists stored data. An agent acting on "read" would not expect a destructive operation, and the description offers no reconciliation of that conflict. This is the exact pattern flagged in the calibration as an annotation contradiction.

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 returned content, then usage, then the cost note — each clause carries information. Minor waste in the parenthetical "same data as the dashboard Competitors tab," but overall tight and well-ordered.

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 read tool with no output schema, the description adequately covers what is returned and why to call it. However, if the destructiveHint were accurate, the omission of any warning would be a serious completeness gap; the description leaves the agent unable to resolve read-vs-destructive.

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 description coverage is 100%, so both site_id and the detail verbosity flag are already documented in the schema. The description adds no parameter-level guidance (it never mentions detail or the top-25 trim), so the baseline 3 applies.

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 the exact resource ("the brand's tracked competitor set") and enumerates the returned fields (domain, link, discovery reasoning), so an agent knows precisely what it gets. It differentiates the content from ad-hoc discovery via "tracked" and "auto-discovered," but never names the sibling discover_competitors, which is the natural confusion point.

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?

"Use before competitive work — content gaps, keyword overlap, backlink comparison (get_backlink_profile on their domains)" gives explicit when-to-use context and routes the agent to a concrete follow-up tool. It lacks a when-NOT-to-use clause (e.g., contrast with discover_competitors for adding new competitors), so it stops short of a 5.

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