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

With no annotations provided, the description carries the full burden. It does disclose a useful behavioral fact: 'No disk access,' which distinguishes this from an actual filesystem existence check. But it stops short of describing return values, outcome form, or edge cases, leaving the agent to guess at the call result. It adds value beyond nothing, but lacks important behavioral detail.

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 extremely efficient: two short sentences front-load the core purpose and the most relevant restriction. There is no filler, repetition, or detail that belongs in the schema. It is both compact and well-structured for quick agent scanning.

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?

Given a tool with nine parameters but no output schema, no annotations, and a description that touches only one parameter, the description is not complete enough. The agent gets no indication about the correct parameter usage amid seven seemingly unrelated input properties, and no clarity on the return result. The broad schema and undefined return value make the tool harder to call safely; the description should clarify that only 'path' matters and what the check returns.

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 the schema already documents all nine parameters. The description reinforces the file-path semantics by saying 'a path to check,' which mirrors the path parameter. However, it does not clarify why numerous unrelated parameters (ref, url, city, feed, host, json, zone, query) are listed, nor which are actually required or relevant, which is a notable gap in parameter semantics.

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 a specific action and target: 'Check whether a path looks safe.' The qualifier 'No disk access' adds an important boundary, and the name/title reinforces the resource. However, it does not define what 'safe' means (e.g., path traversal, syntactically valid), and it does not explicitly differentiate itself from sibling validation tools like browser-url-ok or domain-shape, making it a strong but not perfect purpose statement.

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 guidance about when to use this tool versus alternatives, no prerequisites, and no exclusions or conditions. The description says only what the tool does, not when a caller should reach for it over the many sibling validation tools. The agent is left to infer use from the name and the 'path' parameter.

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