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

Annotations only declare it is a non-read-only, non-destructive, closed-world mutation. The description adds genuinely useful context beyond that: owner-only authorization, a sign-in requirement, and the crucial fact that the tool only *prepares* a credit request which the pro must submit themselves. It does not say whether the lead's status change is reversible.

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?

A single sentence, front-loaded with the access constraint, then the primary action, then the secondary side effect. Nothing wasted.

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?

Covers the essentials for a low-complexity, 3-parameter mutation: who may call it, auth requirement, and that submission is left to the user. With annotations handling the safety profile, the only remaining gap is what a successful call returns or changes.

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 only 33% (only 'evidence' has a description), so the description partially compensates by tying evidence to the credit request. The enum values for 'reason' are self-explanatory in the schema, but 'lead_id' and the distinction between required reason and optional evidence get no added meaning.

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: 'Mark a paid lead as bad and prepare a lead-credit request with evidence.' That clearly distinguishes it from generic siblings like update_lead or log_lead, though it never names an alternative explicitly.

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?

Gives a real prerequisite ('Owners only (needs sign-in)') and implies the trigger condition (a paid lead that is bad), but offers no explicit when-not guidance, e.g. whether to use update_lead instead when the lead just needs editing.

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