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

Annotations only declare destructiveHint=true, but the description adds critical context: the deletion is permanent, assigned members silently fall to a 0 billing rate on Time / Time&Material projects, the tool refuses while the group is in use without force: true, and confirm/confirmation_phrase must be human-supplied. This goes far beyond the single destructive flag and covers exactly what an agent needs to know before invoking.

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 sentences, each carrying essential weight: the action and permanence, the side effects and refusal condition, and the human-confirmation guardrail. The most decision-relevant information (permanence, downstream billing impact, force requirement) is front-loaded, with zero filler.

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 destructive tool with 4 parameters, no output schema, and a safety-critical human-confirmation requirement, the description covers the action, consequences, guardrails, and refusal behavior thoroughly. A minor gap: it doesn't describe the success response, and the recommended non-force workflow (unassign members first) is implied rather than stated. Still, nothing essential to a correct call is missing.

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?

With 75% schema coverage, the schema already documents force, confirm, and confirmation_phrase. The description adds important semantics beyond that: the rule that confirm/confirmation_phrase must never be auto-filled by the agent, and the causal link between force and the refusal behavior. Only pricing_group_id lacks a schema description, but it is self-evident from the tool name and context.

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 opens with 'PERMANENTLY delete a billing rate group from a project' — a specific verb, resource, and scope. It clearly distinguishes this from sibling tools that delete other project entities (projects_delete, projects_delete_material, etc.) and from pricing-group management tools like projects_create_pricing_group or projects_update_pricing_group.

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?

The description explains the refusal behavior ('refuses while the group is in use unless you pass force: true') and implies the safe workflow — members should be moved to another group before deletion. However, it never explicitly names the alternative tool (e.g., projects_unassign_pricing_group or projects_assign_pricing_group) or states 'use X instead when members are assigned,' so the routing guidance is left to inference.

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