fetch_files

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the role-dependent default destination (fleet exchange folder for a lead, own inbox for a manager) and that the default source is the outbox, which is genuine value. But it omits whether source files are removed, whether destination files are overwritten, permission requirements, and what happens if agent_id is invalid or the agent has no deliverables.

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 short sentences, front-loaded with the operation and followed by the default-destination rule. No filler and no restatement of the tool name.

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 file-transfer tool with no annotations and no output schema, the description covers source and destination semantics adequately but leaves the required agent_id opaque and says nothing about overwrite behavior, error conditions, or what the tool returns. That is enough to attempt a call but not enough to call it confidently in edge cases.

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 0%, so the description must compensate, and it partially does: it explains that 'paths' selects specific deliverables versus the whole outbox, and that 'dest' defaults to a role-specific folder rather than the empty string the schema shows. The required 'agent_id' parameter is never explained — whose id it is and what constraints apply — leaving the most important input undocumented.

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: copy the agent's deliverables (outbox or named paths) to a destination. This is clearly a transfer operation and is distinguishable from list_files and send_files by direction, though the description never names those siblings explicitly. Minor friction: the name says 'fetch' while the description says 'copy', leaving ambiguous whether files are moved or duplicated.

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?

Conveys the default behavior well (outbox when no paths given; role-dependent destination), which implicitly tells the agent the common call pattern. However there is no explicit when-to-use vs list_files/send_files guidance, no statement of prerequisites such as whether the source agent must be finished, and no exclusion cases.

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