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

The description discloses genuinely useful behavior (cascade deletion of 'owned sound cues' and project scoping), but it directly contradicts the annotations: destructiveHint=false means 'additive updates only' per the MCP spec, while this tool removes a graphic and deletes its sound cues. See 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?

Two sentences, with the scoping constraint front-loaded before the core action, and no filler. Every clause carries information (scope, action, cascade), which is tight for the payload.

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 mutation tool with no output schema, it covers scope, the cascade behavior, and the return ('returns the project identity with its result'). It omits error handling (unknown id) and reversibility, which are the only meaningful remaining gaps.

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 50%: project_id is fully documented in the schema and reinforced by the description ('acts only on the explicit project_id'), while id remains undescribed in both places and the description only echoes 'by id' without format guidance. Baseline 3 is appropriate for a two-parameter tool with partial coverage.

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 sentence 'Remove one motion graphic by id together with its owned sound cues' gives a specific verb (remove), a specific resource (motion graphic), and the identifier used. It distinguishes itself from sibling removes such as remove_editorial_graphic and remove_vector_graphic through the resource noun, though it never contrasts them 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?

The 'PROJECT-SCOPED' line explains how the scope argument works, but nothing states when to choose this tool over set_motion_graphic (edit in place) or the other remove_* siblings. No preconditions, no exclusions, no alternatives are offered.

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