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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real value: it discloses the scored 0-100 + A-F report with severities and ranked recommendations, and notes the scan is self-contained and runs straight away. Minor gap: it does not say how long a full scan takes or how it behaves on a large site, though the time/ceiling hints live only in the schema.

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?

Front-loaded with the five scan areas and then the report shape, with almost every clause carrying information. It is a dense single paragraph that is a bit long, and the deep=true explanation partially duplicates the schema.

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 no output schema, the description supplies the missing return contract — score, grade, severities, ranked recommendations — and states the scope and safety profile. An agent could select and call this correctly with no further reading.

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% and each parameter already carries its own description with defaults and ceilings, so the schema does the heavy lifting. The description restates the deep=true behavior (all plugins/themes + wider tree) but adds nothing on checks, max_files, or max_seconds.

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 ('scans this WordPress site for security and malware problems') and then enumerates the five distinct audit areas, so the agent knows exactly what is covered. It also disambiguates scope ('scans this site only') against the fleet-wide siblings.

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 context is clear: single-site scanning, read-only, runs immediately without a confirmation handshake. However, no sibling is named — an agent choosing between this, fleet__scan_security, and emcp-tools-get-hardening-status (which overlaps the hardening area) must infer the split rather than being told.

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