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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld, so safety is covered. The description adds genuinely new behavioral context beyond them: the k-anonymity mechanism (only a hash prefix is sent), the rule that a breached password is always rated very_weak, and the transport guarantee that the password goes in a POST body and never a URL. This is strong, non-obvious disclosure; it stops short of only omitting the exact return shape.

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?

Every clause earns its place: the scoring factors, the optional breach behavior with its privacy mechanism, the routing to siblings, and the transport note. It is front-loaded with what the tool does before moving to alternatives and security caveats, with no filler sentences.

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 two-parameter, no-output-schema scoring tool, the description covers purpose, the breach side-effect, privacy, and routing. The main gap is that it does not describe the shape of the result (e.g., the strength bucket vocabulary such as very_weak, or whether entropy is returned numerically), which an agent may need to interpret output.

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 baseline is 3. The description goes beyond the schema by explaining the consequence of check_breach=true (a Have I Been Pwned lookup via k-anonymity) and the override behavior where a breach forces a very_weak rating, which the schema's one-line parameter description does not convey.

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 (scores) and resource (password strength) and enumerates the factors used: length, character variety, entropy as an upper bound, repeated patterns, and per-word passphrase estimation. It also names the exact siblings it must not be confused with (password_breach, password), so an agent can disambiguate without opening any schema.

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?

Explicitly gives the when: 'Use it to evaluate a password someone is choosing', and names the alternatives with their selecting conditions: password_breach 'when you only need the breach count' and password 'to generate a new one'. This is textbook when/when-not/alternatives guidance.

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