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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds genuinely non-redundant behavior: results are sorted newest first, each row carries status and signed video links, and the call is free (no credit consumption).

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?

Three short clauses with zero filler: what is returned first, pagination second, cost last. Front-loaded and every clause carries information an agent can act on.

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 usefully names the returned fields (status, signed video links) and the ordering, plus the cost model. Remaining gaps are minor — no mention of what an empty page or expired links imply, and no explicit pointer to get_project for single-item retrieval.

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 100%, so all five parameters are already documented (tool, limit, query, cursor, status with enums). The description only echoes cursor semantics ('nextCursor'), adding no filtering or formatting detail beyond the schema — the baseline 3 for schema-complete tools.

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?

Specific verb+resource: 'List the account's projects', plus scope (account-level), ordering (newest first), and payload contents (status, signed video links). It is clearly distinct from the singular get_project sibling by plural/list framing, but never names or contrasts the alternative explicitly.

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?

Usage is implied rather than stated: pagination mechanics ('Paginate with cursor (nextCursor)') and the 'Free' cost note hint at when this is attractive over credit-spending generation tools. There is no explicit when-to-use/when-not guidance or routing to siblings like get_project for a single record.

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