Read an email thread

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

With no annotations, the description carries the full burden. It usefully discloses what a call returns (all messages, headers, body, attachments parsed), which is real behavioral context, but says nothing about read-only nature, auth/scope requirements, quota cost, or how large threads or attachment payloads are handled.

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?

One sentence, front-loaded with the verb 'Fetch', no redundancy, and the parenthetical efficiently enumerates the parsed payload contents. Nothing to trim.

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?

Adequate for a three-parameter read tool with a fully covered schema and no output schema — the sentence explains roughly what comes back. It nonetheless omits thread-vs-message ID provenance and any efficiency caveat for large threads, leaving the agent to discover behavior empirically.

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 baseline is 3. The description adds only marginal parameter meaning: 'full conversation thread' loosely mirrors the format enum default of 'full' but does not explain metadata/minimal tradeoffs or the account nickname parameter.

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+resource ('Fetch a full conversation thread') and goes further by saying every message is parsed with headers, body and attachments. It clearly implies thread-level retrieval rather than message-level, but it never names the siblings it differs from (google_gmail_get, google_gmail_threads_list), so differentiation is left to inference.

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?

No when-to-use guidance at all. An agent is not told when to pick this over google_gmail_get (single message) or google_gmail_threads_list (list threads), nor whether an ID must come from the list call. Context is implied by the name only.

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