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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so this is added context rather than baseline disclosure. The description goes further: it specifies the fields in each finding (kind, severity, location), a privacy-relevant output constraint (injection phrases quoted only up to 80 characters, never surrounding content), a degradation behavior (`checks_run` lists what was inspected; uncheckable file type returns `overall_risk: unknown`), an explicit non-guarantee, and a per-file cost of 0.01 USDC. That is exactly the class of information structured fields do not carry.

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?

It is front-loaded: the enumeration of what is searched comes first, then reporting behavior, then limits and price. Nearly every clause carries information an agent needs. The trailing "MCP tool: `scan_file`" restates the name and earns nothing, a small but real waste.

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 one-parameter tool with no output schema, the description supplies the return shape (finding kind/severity/location, `checks_run`, `overall_risk`), the failure mode (`unknown`), the cost, and an honest scope limit. Nothing an agent needs in order to call it and interpret the result is missing.

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?

There is a single parameter and schema description coverage is 100%, with the 4 MiB cap already documented in the schema, so the baseline of 3 applies. The description does add meaning about accepted input formats (PDF, Office, image, text/HTML), which helps an agent decide what bytes are valid, but it adds nothing about encoding or required content shape beyond the schema.

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 names a concrete verb (looks inside) and an explicit scope: PDF/Word/Excel/PowerPoint, image, text/HTML, searching for scripts, launch actions, hidden text, embedded files, trailing data and injection phrases. That enumerates exactly what gets inspected, which is far more than a restatement of the title. It does not, however, position itself against near-neighbors like scan_metadata, check_redactions or scan_metadata-adjacent tools, so an agent must infer the boundary.

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?

Usage is only implied: an agent would reasonably conclude this is a pre-read triage step before processing an untrusted file. There is one genuine exclusion ("Not an antivirus"), which usefully rules out malware-analysis intent. But there is no statement of when to prefer this over check_redactions or scan_metadata, and no prerequisites described.

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