Attach files

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

The annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so safety direction is covered and the description does not contradict it. The one piece of behavior the description adds is that files are sourced from the local machine, which matters for an open-world tool. It still omits practical context an agent needs before calling: file size or type limits, whether the attachment is copied or linked, and what happens when a task or path is invalid.

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 with no filler, with the primary action in the first clause and the optional parameter flagged at the end. Nothing is repeated from the title or schema. Its brevity dips into under-specification rather than padding, so it is efficient but not exemplary.

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 three-parameter mutation tool with no output schema and moderate schema coverage, the definition is minimally viable. It names the action, the source of the files, the target, and the optional note. It leaves out failure modes, limits, and what the tool returns on success, which an agent would need to plan around and to verify.

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 description compensates for only one gap. It tells the agent that the third parameter is an optional note, so the undocumented 'comment' parameter can be inferred. It adds nothing about 'paths' beyond 'files to attach', and the maxItems=10 and maxLength=5000 constraints exist only in the schema. Baseline 3 is the right score, because the schema already documents task and paths well.

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 (files), plus the source ('from this computer') and the target (a task). That is far clearer than the title restated. It does not explicitly differentiate itself from siblings, but 'attach files to a task' is distinct enough from add_comment and update_task that an agent can place it without help.

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?

There is no when-to-use or when-not-to-use guidance. The description never says whether this tool should replace, supplement, or be used alongside add_comment when an agent wants to convey information about a task. Prerequisites (does the task have to exist or be open? does the file have to exist locally?) are unstated. 'from this computer' hints at local-path semantics but is not framed as a usage rule.

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