save_attachment

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

Annotations already declare idempotentHint=true, so the description's 'Idempotent when already saved' reinforces but adds minimal new information. The description does not disclose other behavioral traits beyond what annotations provide, such as whether the operation requires any specific permissions or what happens if the attachment does not exist. Given the good annotation coverage, the description adds little extra value.

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 extremely concise: two sentences. The first states the purpose immediately, and the second adds a critical behavioral note (idempotency). Every word serves a purpose, and it is front-loaded with the primary action.

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?

Given the low complexity (one parameter, good annotations, output schema exists), the description is nearly complete. It covers the core purpose and key behavioral trait. It could optionally mention that the attachment must exist or what the output is, but those are covered by the output schema.

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 100% with a description for 'attachmentId' ('a string that will be trimmed') in the input schema. The tool description does not mention parameters or add meaning beyond the schema. The baseline of 3 is appropriate since the schema already documents the parameter adequately.

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 clearly states 'Save/bookmark an attachment for later reference.' The verb 'save/bookmark' is specific and the resource 'attachment' is unambiguous. It distinguishes from siblings like 'add_attachment' (which adds an attachment to something) and 'unsave_attachment' (which removes the saved bookmark).

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 provides clear context: use this when you want to save or bookmark an attachment for later reference. It also notes idempotency ('Idempotent when already saved'), which guides behavior on repeated calls. However, it lacks explicit exclusions or comparisons with similar tools like 'pin_attachment' or 'save_message'.

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