Watch a directory for new files

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

The description discloses the polling loop and both exit conditions (new file or max iterations), which is useful. However, with no annotations, it does not specify what constitutes a 'new' file (e.g., based on mtime or creation), whether SSH requires credentials, or if the tool blocks. This is acceptable but not deep.

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 a single sentence that is front-loaded with the primary action ('Poll a directory') and specifies the completion criteria without unnecessary words.

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 simple poll task, the description covers the core loop but leaves some behavioral details unspecified (e.g., recursive watching, return value). Given no output schema or annotations, this is minimally viable.

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?

The schema already provides 100% coverage and descriptions for all four parameters. The tool description adds no additional parameter semantics beyond the schema, so the baseline of 3 is appropriate.

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 it polls a directory and completes when new files appear or after max iterations. This is a specific verb-resource pair with clear termination conditions, distinguishing it from sibling tasks like pattern matching or tailing.

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?

No explicit guidance on when to use this tool versus alternatives like tmux_wait_for_pattern_task. The usage is implied by the directory-polling behavior, but it does not state exclusions or preferred scenarios.

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