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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description still adds real behavioral facts not present in the annotations: that it acts only on an explicit project_id (never the active-project pointer) and that the result carries the project identity — useful scoping and return context. It does not, however, explain the notable idempotentHint=false on a read tool.

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?

Front-loads the two most important framing facts (project scoping, read-only) and then lists query modes. It is a single dense run-on sentence, but little is wasted.

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 no output schema, the description should carry return-shape burden; it only says the project identity is returned and says nothing about result count, ordering, or the 'k' cap. For a read-only search tool with annotation coverage this is adequate but incomplete.

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 very low (14%), so the description must compensate, and it partially does: it gives semantics for 'like' (program seconds or key@seconds, same framing on another day), 'night' (true/false), 'faces' (close|medium|wide|none), and 'query' (word over the storyboard). But 'circles' and 'k' are enumerated with no meaning, leaving clear gaps against the 7 parameters.

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?

Names a specific verb and resource — 'recall shots in the main video and the project's clips' — and frames it as a filter-based recall over footage. An agent can tell it retrieves shots rather than editing them, though it never explicitly names the nearest siblings (get_shots, find_visual_moments, find_footage) to differentiate scope.

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?

There is no when-to-use/when-not guidance and no comparison to alternatives like get_shots or find_visual_moments. The 'PROJECT-SCOPED'/'READ' prefixed labels hint at context, but nothing tells the agent which of several shot-finding tools to pick.

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