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

Annotations already establish readOnly=true, destructive=false and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the beta status with a date, per-tier export allowances, and the shape of list output ('summaries; full=true for whole documents'). The quota sentence is somewhat tangential to a listing tool but still discloses account-level constraints.

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?

The action catalog is front-loaded and the prerequisite clauses are compact, so the agent hits the important routing information immediately. The beta/export-quota sentence is longer and more promotional than the rest and is only loosely relevant to a project-listing tool, which keeps it out of the top band.

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 5-parameter, multi-action read tool with no output schema, the description covers all action variants, their required IDs, the return granularity toggle, and points to video_guide for the full schema and tier notes. Nothing essential for a correct invocation is missing.

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 0%, so the description must carry the burden and largely does: it explains the action enum, which actions require projectId, that revision needs projectId+revision, that brand needs brandId, and what full=true changes. It stops short of stating types or that additionalProperties are ignored, but the required/optional combinations are clear.

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 the resource (projects, brands, looks) and enumerates every action with a one-line meaning each ('list returns one summary per project', 'get/history need projectId'). An agent can tell this is the read-surface for Video Director, though the write counterpart (video_project_write) is never named outright.

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 per-action prerequisites (get/history need projectId, revision needs projectId+revision, brand needs brandId) and directs the agent to 'Call video_guide first for the catalog'. That is actionable routing, but it never states when NOT to use this tool or how it differs from siblings like video_project_write or video_delete.

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