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

The description adds substantial behavior beyond the readOnlyHint: large timelines return a compact index instead of invalid truncated JSON, aliases are accepted without retry, and compact=true changes the response to include counts, caption state, and duplicate assets. This is valuable information that cannot be inferred from annotations alone.

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 description is dense but front-loaded with the most important constraint, PROJECT-SCOPED, and every subsequent sentence adds a distinct behavior: full result, large-timeline fallback, section selection, aliases, and compact mode. There is no filler or repetition.

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 read tool with no output schema, the description covers scope, pagination, section selection, aliases, compact mode, and large-timeline behavior. It is slightly less explicit about the exact default response shape when no sections are requested, which keeps it from being fully complete.

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 only 40%, but the description compensates for every parameter. It explains that project_id is the immutable explicit scope, defines offset/limit as pagination for list sections, gives alias mappings for sections, and specifies compact=true's behavior. This adds meaning far beyond the bare schema types.

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 is specific about the resource and action: it reads the current EDL JSON and version for a project. It also distinguishes the call from siblings by emphasizing project scoping, explicit project_id, and result identity, so an agent can tell it apart from related getters.

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 description gives concrete usage instructions: request top-level sections, paginate list sections with offset/limit, use natural aliases without retry, and use compact=true for counts, caption state, and duplicate assets. It also points to get_edit_plan as the alternative for creative-plan data and warns that feature/tool names are not valid sections.

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