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

Annotations already declare readOnlyHint=false, openWorldHint=false and destructiveHint=true, so the safety profile is covered. The description adds genuinely new behavioral context the annotations cannot convey: per-file and per-board size quotas that vary by plan (Free vs Pro) and server-side photo optimization. It does not mention failure behavior when limits are exceeded, which is the one notable gap.

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 compact sentences, front-loaded with the core action before the quota detail, and every clause carries information. 'Photos are optimized, as in the app' is mildly informal filler but still communicates a real side effect, so it earns its place.

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 mutation tool with no output schema, the description covers input modes, size constraints and transformation behavior, while annotations cover the destructive/read-only profile. What is missing is error/limit-exceeded behavior and any permission requirement, which would be the remaining useful additions.

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 67%, so roughly a third of parameters are undocumented in the schema. The description compensates by explaining the pairing semantics — url for links, contentBase64 + filename for files — which the schema lists as independent properties without stating they are alternatives. Undescribed parameters (mimeType, name) remain slightly ambiguous, but the mode distinction is the critical semantic.

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 (attaches) and resource (link or file) and names the target object (a task), so an agent immediately knows what the tool produces. It also distinguishes the two input modes, url vs. contentBase64 + filename, which is the key ambiguity for this tool. The verb 'add_attachment' is unambiguous against siblings like delete_attachment and rename_attachment despite no explicit naming of them.

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 implies usage by mapping each mode to its parameters (link via url, file via contentBase64 + filename), which tells the agent how to pick a path. However, it never states when to prefer this over sibling alternatives such as create_embed or add_comment, nor any prerequisites (e.g., board membership or permissions). Usage is inferable but not stated.

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