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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful context beyond that: it acts only on the explicit project_id (never the active-project pointer) and returns the project identity alongside the result, which is real behavioral information an agent needs.

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 tightly packed sentences with the scope constraint and READ nature front-loaded. Nothing is redundant, though the second sentence's dense shorthand costs some readability without being wasteful.

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?

With four parameters (three required), no output schema, and only 25% schema coverage, an agent still cannot tell what start and end mean or what the return contains besides an identity echo. For a selection tool with several near-name siblings, the definition leaves too much unspecified to call it correctly on the first try.

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 25% (only project_id is documented), so the description must compensate. It does document the box parameter's format as [x0,y0,x1,y1], which the schema leaves opaque, but the required start and end parameters get no explanation at all (frame indices? seconds? a range?). Partial compensation earns a middle score.

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 READ marker and 'the frame to freeze for a poster' convey that this selects a still frame, but the rest ('sharp in its window, the lockup box clear and off the face') is selection-criteria jargon rather than a purpose statement. It does not distinguish itself from siblings like add_freeze_frame, animate_still, or set_frame, so an agent cannot tell which one to reach for from the description alone.

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 preamble tells the agent the call is scoped to project_id, which is mild usage context, but there is no when-to-use, when-not-to-use, or pointer to an alternative among the many still/frame-related siblings. The agent gets no help deciding between pick_still and add_freeze_frame or set_frame.

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