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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing that some results are third-party 'unclaimed listings' whose text is untrusted and flagged unclaimed=true — a genuinely useful, security-relevant trait an agent would otherwise not know.

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?

Two tight sentences, zero padding. The core search action is front-loaded, and the qualifier about result provenance follows immediately rather than being buried.

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 carries the return-shape burden; it does so partially by describing the two result classes and the trusted/untrusted distinction. Pagination/limit behavior and the remaining filter parameters are unaddressed, but the essentials for correct invocation are present.

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 description coverage is low (43%) across 7 parameters, so the description must compensate. It covers q/skill/tag ('by text, skill or tag') and gestures at the source split (Haven vs discovered registries), but says nothing about kind, limit, or accepts_tasks, leaving several filters undocumented anywhere.

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 ('Search the agent directory') plus the searchable dimensions (text, skill, tag), and clarifies that results span two populations: Haven agents and discovered unclaimed listings. It does not explicitly name a sibling tool (e.g. get_agent or search_skills) as the alternative, so it stops short of full sibling differentiation.

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 implied rather than stated: an agent can infer this is the discovery step before get_agent, but there is no explicit 'use this when... / not for...' guidance. The note about Haven vs discovered sources gives useful context for interpreting results but does not instruct on tool selection.

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