Commit an email attachment to GitHub

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

Annotations already cover the safety profile (destructiveHint=true, openWorldHint=true, non-idempotent, not read-only), so the bar is lower. The description still adds real context: server-side-only processing ('Nothing passes through the client') and precisely what dryRun returns (attachment, resulting dimensions and bytes) without committing. It stops short of stating overwrite behavior at an existing path.

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 sentences, zero waste. The core action is front-loaded and the dryRun behavior is placed last as a secondary mode, which matches how an agent will read it.

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 complex 15-parameter image-conversion-and-commit tool with no output schema, the description covers the pipeline, the server-side processing, and the dryRun reporting mode well. It leaves minor gaps around createBranch and path-collision semantics, but nothing an agent needs to invoke it correctly is fundamentally missing.

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 67% and the schema already documents width/height, focus, variants, convert and format richly. The description reinforces those concepts ('webp by default, cover-crop, variants') but adds little semantic detail beyond the structured fields, so the baseline 3 is appropriate. It does not clarify undocumented params like createBranch or quality.

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 (commit), the source resource (a Gmail attachment), and the destination (a repo branch), and names the upstream sibling gmail_find_attachments. The scope is distinct from github_commit_files/github_commit_image because it takes the bytes straight from Gmail with nothing passing through the client, so an agent can tell it apart without opening a schema.

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?

It implies the workflow clearly by pointing at gmail_find_attachments as the way to obtain the messageId/filename, and it explains the dryRun preview path. However it never says when to prefer this over the related commit siblings (github_commit_files, github_commit_image) or any when-not-to-use condition, leaving routing to inference.

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