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

The annotations already flag destructiveHint=true, but the description adds two things they don't cover: the retention semantics ('Past results keep it') and the mandatory preview-then-confirm protocol. That is non-obvious behavior an agent would otherwise have to guess, so it clears the lowered bar for annotated tools.

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?

Three compact clauses, front-loaded with the action and its effect, and no sentence is filler. The telegraphic fragment style ('confirm: true applies') is slightly cryptic, which holds it below a 5.

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-param destructive tool with no output schema, it covers the action, retention behavior, and the safety protocol, which is most of what an agent needs. It omits edge cases such as an unknown competitor name, and the brand-scoping caveat is left entirely to the schema.

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% and every parameter already carries a descriptive string, so the schema does the heavy lifting and baseline 3 applies. The description's 'by name or domain' and 'confirm: true applies' largely restate what the competitor and confirm schema entries already document.

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+resource ('Stop tracking a competitor') with the accepted identifier forms ('by name or domain'), which maps cleanly onto the required parameter. It is trivially distinguishable from siblings add_competitor and get_competitors without opening any 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?

'Preview first; confirm: true applies' prescribes the exact call sequence for a destructive operation, which is real when-to-use guidance. It does not name an alternative or state exclusions (e.g., a tool for pausing instead), so it falls 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.