read_attachment

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

Annotations already declare readOnlyHint and openWorldHint, so the lower bar applies; the description still adds real value by disclosing that only certain MIME types yield text and that others return metadata only — a behavioral outcome the agent cannot infer from annotations. It omits that output is truncated at max_chars (default 20k), though the schema carries that.

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?

Two sentences, zero waste, with the core action and the format caveat front-loaded before the short provenance note. The parenthetical format list earns its space by defining the tool's actual capability boundary.

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?

No output schema exists, and the description does cover the key return-shape distinction (text vs. metadata-only), which is the main thing an agent needs to interpret results. It could have mentioned that long extractions are truncated per max_chars, but overall it is sufficient for correctly invoking and reading this tool.

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%, so the baseline is 3. The description's note that the index originates from read_message duplicates the schema's own wording, and it says nothing about uid, folder, or max_chars, so it adds no meaning beyond the structured field definitions.

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 and resource ("Read the text of one attachment of a message") and immediately bounds the scope with the supported format list plus the fallback behavior for other types. An agent can distinguish this from read_message (message body) and from list_folders/search 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?

"Index comes from read_message" supplies the prerequisite workflow, making clear this is a follow-up call to a message read rather than an entry point. It stops short of naming exclusions (e.g., 'do not use for message bodies, use read_message'), so it is clear context but not a full when/when-not routing statement.

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