watch

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

With no annotations, the description carries the full burden and does well: it discloses that start returns a watch_id, that poll blocks up to wait_ms, and that events are coalesced per path so a triple-save is reported once. It omits error/failure behavior and permission requirements, so it's strong but not complete.

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 dense sentences with no waste, front-loaded with the tool's purpose before the action semantics. Every clause (watch_id return, poll blocking, coalescing) 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 10-parameter, multi-action tool with no annotations and no output schema, the description covers the action lifecycle and key behaviors adequately. It doesn't describe the shape of returned events, but it covers enough for correct invocation.

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 100%, so the schema already documents all ten parameters with per-action notes and defaults. The description adds only the coalescing and blocking semantics, so the baseline 3 applies.

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 ('Watch a file or directory for changes') and enumerates the four sub-actions, so the tool's scope is unmistakable. It doesn't explicitly contrast itself with siblings like fs_list or search_files, which keeps it short of a 5.

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?

It tells the agent how to use poll effectively ('one call replaces a polling loop') and what each action does, which is genuine usage guidance. However, there is no explicit when-to-use-this-vs-alternatives or when-not, so it stays at implied usage.

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