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

Annotations already cover readOnlyHint=true and destructiveHint=false. The description adds valuable context: the 400-word cap, pagination hint, and the fact that the result includes the project identity. No contradictions with annotations.

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 dense sentences, front-loaded with scope and key constraints. Every clause adds information—no filler or repetition. The emphasis via uppercase is purposeful.

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 simple tool with 3 params and no output schema, the description covers scope, cap, pagination existence, and the 'source of truth' role. Missing details like time units and pagination mechanics are minor for an agent selecting the tool, and the description gives enough to call it correctly.

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 only 33% (only project_id is described). The description implies start and end define a 'source-time range' and that the response caps at 400 words, but it doesn't specify units, whether they're required for pagination, or their exact semantics. It partially compensates but leaves gaps.

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 states a specific verb ('get'), resource ('words'), and scope ('project-scoped'), and clarifies it returns word-level timestamps with time ranges. It explicitly distinguishes itself from sentence-based timing by declaring itself 'THE source of truth for cut points inside a sentence', making its unique purpose clear.

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 a clear directive to use this tool for word-level timing and never estimate from sentence ranges, which is an actionable exclusion. However, it doesn't name specific sibling tools (e.g., get_transcript) as alternatives, so the guidance is implicit rather than explicit.

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