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

Annotations already declare readOnlyHint and idempotentHint, but the description adds substantial behavioral context beyond that: it distinguishes evidence classes ('verified', 'observed', 'declared'), explains that self-declarations are never presented as verification, states that anonymous and credentialed callers get identical matches (credential only unlocks the introduction action), and reveals that requireHumanConsent cannot be bypassed. It also notes that certain fields (geography, budget, etc.) carry no verification weight. No contradiction with annotations.

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 longer than typical but densely packed: the first sentence outlines the tool's return value, the second explains evidence classes, the third addresses anonymity vs credentials, and the fourth defines the public-directory scope. Every sentence earns its place for a tool with 9 parameters and no output schema. Slightly verbose but not wasteful.

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 the tool's complexity (9 params, no output schema), the description covers the output essentials: match reasons, proof evidence, endpoint health, next action, and public-directory exclusion. It also addresses edge behaviors (anonymous access, consent requirement, non-verifiability of certain filters) that an agent must know to select and invoke the tool correctly. Missing return format is acceptable because no output schema exists and the description names the key result components.

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?

The input schema covers 100% of parameters with rich descriptions, including caveats like 'Never a hard filter' for need and explicit notes that geography/budget/responseTime/requiredCapability are matched against self-declared text. The tool description itself adds little param-specific meaning, as the schema already does the heavy lifting. Baseline 3 is appropriate.

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 opens with 'Finds published Mixer4AI agents for a business need', giving a specific verb (finds), a specific resource (published Mixer4AI agents), and a clear outcome (returns match reasons, verification evidence, endpoint health, next action). It also clearly distinguishes itself from siblings by stating it only returns published public-directory cards and explicitly contrasts its tier filter with search_directory's exact-match filter in the parameter description.

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?

The description conveys clear usage context: 'Finds published Mixer4AI agents for a business need' and 'Returns only agents their owning principal has published to the public directory'. It also clarifies behavior for anonymous vs credentialed callers. While it doesn't explicitly say 'use this instead of search_directory', the in-parameter comparison to search_directory provides an exclusion signal. No misleading guidance.

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