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

The description does add legitimate context beyond the annotations (project becomes the returned identity, stills are attached, project_id is never inferred from the active-project pointer). However, it labels the call 'WRITE-free' while the annotations declare readOnlyHint=false and idempotentHint=false, i.e. the tool is explicitly not read-only. That is a direct conflict about write behavior, so per the rubric this dimension is capped at 1 and is flagged as an 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 dense clauses, front-loaded with the safety tags, so nothing is buried. But the compressed tag style ('PROJECT-SCOPED', 'WRITE-free') is cryptic and one of those tags is also inconsistent with the annotations, so brevity comes at the cost of clarity.

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 4-parameter render tool with no output schema and low schema coverage, the description does cover the essentials: scope, that results come back attached as stills, and which call applies the pick. It omits what n/id/axis actually control and gives no hint about rendering cost or latency, and the contradictory 'WRITE-free' tag undermines confidence in the rest of the disclosure.

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 25% — project_id is the sole documented parameter. The description reinforces project_id scoping and rules out pointer-based guessing, matching the schema text, but says nothing about n, id, or axis; 'three type voices' only loosely hints at the count default and the 'voice' enum value. With coverage this low the description needed to compensate more than it does.

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?

It states a concrete operation — rendering three type-voice variants of one typeset lockup as stills — and distinguishes itself from set_typeset, which is the call that applies the pick. The phrasing is heavily jargonized ('type voices', 'typeset lockup', 'real frame') and never says plainly that it produces options for review, so an agent unfamiliar with the domain has to infer the point.

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 gives clear workflow context: results are attached so the agent can show the user, and the chosen variant is applied via set_typeset, which effectively names the alternative action. There is no explicit when-not-to-use or guidance on choosing this over near-neighbors like make_variant_set or pick_still.

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