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

Annotations already declare this a non-read, non-open-world, idempotent, non-destructive operation, so the safety burden is largely carried elsewhere. The description adds value beyond them by disclosing that the call is strictly project-scoped and that the result carries the project identity — useful return-shape information given there is no output schema. It does not resolve the tension between "Remove" and destructiveHint=false (reversibility/undo, missing-id behavior), which keeps it out of the top band.

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 no filler, and the scoping rule is front-loaded in caps so the constraint is seen before the action. The capitalization is stylistically heavy but does not cost comprehension.

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 2-parameter mutation with no output schema and one undocumented parameter, the description covers the scope rule and the return payload but leaves the id's referent ambiguous and says nothing about failure modes (card not found, already removed) or whether the removal is reversible. Adequate but with visible 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 description coverage is only 50%: project_id is well documented in the schema, while id has no description at all. The description says "by id" but never clarifies whether that id is the card id (as opposed to a project or asset id), so it only partially compensates for the coverage gap. Baseline 3 for a 2-param tool with partial schema 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 description names a specific verb ("Remove") and resource ("footage card") and identifies the lookup key ("by id"), so an agent can distinguish it from the many add_*/set_* siblings in the same namespace. The only friction is the vocabulary mismatch between the tool name ("picture_card") and the description ("footage card"), which forces a small inference about whether these are the same object.

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?

It states a real usage constraint — the call is project-scoped and must receive an explicit project_id, never the active-project pointer — which is actionable guidance. However, it never says when to remove versus update a card (set_picture_card), nor what preconditions or alternatives exist, so the selection guidance against siblings is only implied.

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