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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world. The description adds useful behavioral scope beyond annotations: variable types, binding syntax, and the fact that track-local lets are not listed. It reinforces 'does not write', which is redundant with readOnlyHint but harmless.

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?

Four short sentences, front-loaded with the core list/read action. The types and binding notes are useful context, though the final 'Does not write' is somewhat redundant with annotations. Overall no wasted prose.

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 two-parameter read-only tool with full schema coverage and rich annotations, the description covers purpose, usage modes, data types, and scope exclusions. Nothing critical is missing for correct invocation.

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 the schema already documents name and projectId semantics, including null behavior. The description only paraphrases 'pass name to read one' and adds no syntax, format, or constraint beyond the schema.

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?

States a specific verb 'List' and resource 'film-root lets (project variables)', and distinguishes the single-read mode ('pass name to read one'). It explicitly excludes track-local lets and writes, differentiating it from siblings like write_variable.

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?

Gives clear conditions: omit or null name to list, pass name to read one, and exclusions for track-local lets and writes. It does not name a specific alternative tool (e.g., read_film) for related film variables, so alternatives are implied via exclusions rather than explicit.

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