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

Annotations already declare non-read-only, non-destructive, non-idempotent. The description goes beyond them by disclosing the required correction:write scope and that the result is a moderated correction record, which tells the agent the write may not be immediately visible. It doesn't cover idempotency or duplicate-handling behavior.

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 short sentences with no filler: the action and the key behavioral facts are front-loaded. Every clause earns its place.

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 5-parameter mutation tool with no output schema and 20% schema coverage, the description covers auth and outcome but leaves parameter usage and the moderation/duplicate workflow unexplained. Adequate but with real gaps an agent would need filled elsewhere.

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 only 20% and the description names none of the five parameters (slug, old_price, new_price, evidence_url, agent_name). 'Evidence-backed' loosely gestures at evidence_url but does not explain formats, pairing of old/new price, or the agent_name fallback behavior, so the description fails to compensate for the schema gap.

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 ('Report an evidence-backed aicoolies price change') and names the sibling submit_correction, so the agent can tell it is a specialized price-change path. The differentiation is a bit blurry since it produces the same record, but the purpose itself is unambiguous.

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?

Names the alternative (submit_correction) and supplies the auth prerequisite correction:write, giving the agent clear context for when this path is reachable. It stops short of an explicit 'use this instead of X when...' rule, so a 4 rather than a 5.

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