monitor_file_metadata

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds genuinely useful behavioral context: this is repeated *polling* over an interval, not a one-shot read, and it is restricted to a single file. It still omits anything about rate/interval cost or what a poll cycle returns over time.

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 plus a scope-exclusion clause. The read-only, single-file constraint is front-loaded and every sentence carries distinct information; nothing is padded.

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?

With an output schema present and rich annotations, the description needn't explain return values, and the scope/exclusion statements cover the main misselection risk. It is nearly complete for a 3-param tool; only the polling-semantics cost is left implicit.

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 100%, so path, duration_seconds, and interval_seconds are already fully documented in the schema. The description restates the path requirement but adds no syntax, format, or bounds detail (e.g., polling cost of duration × interval) beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 precise verb and resource ('READ-ONLY polling of one FILE's size and timestamps') and explicitly scopes it to a single file, not a directory. The negative framing ('not a directory scan, access tracing, or a delete/modify operation') actively separates it from siblings like analyze_file_distribution.

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?

Makes the triggering condition clear: the agent must have the exact file path, and it is not a directory scan or a tracing/delete operation. It rules out whole classes of misuse but does not name a specific alternative sibling to use when a directory-level view is wanted.

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