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

Annotations already mark the tool as readOnly, and the description adds valuable non-obvious behavior: the transcript is full while the summary is truncated to 6000 chars, the exact return fields are listed, and no-match returns `{'meeting': None}`. This goes beyond what the schema alone conveys.

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 well-structured: a summary block front-loads the core purpose and usage trigger, and a returns block efficiently documents the output shape. The sales-call example is concrete and earns its place without bloating the text.

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 single-parameter, readOnly tool with no output schema, the description is complete: it explains when to call it, what input to provide, exactly what the returned dict contains, and the no-match behavior. An agent has everything needed to invoke 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?

The input schema fully documents `meeting_id` as the id from `search_meetings` results, and description coverage is 100%. The description's mention of the meeting id appearing in the return adds minimal extra meaning 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?

The description states a specific action ('Fetch the full, untruncated transcript for a single meeting') and clearly differentiates the tool from `search_meetings`, which returns only a truncated preview. This makes the tool's role unambiguous even among many sibling get_* tools.

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 explicitly says to use it after `search_meetings` when the 10000-char transcript preview was cut off and full spoken words are needed, with a concrete sales-call example. It does not mention when not to use it or name alternative transcript tools like `get_run_transcript`, so it stops short of a full exclusion set.

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