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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is covered. The description adds real value beyond that: it names the return payload shape and explicitly states no task or probe executes, which is the key behavioral distinction from verification tools.

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 with zero filler; the core purpose is front-loaded and the return contract follows immediately.

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 read-only search tool with no output schema, this covers purpose, payload, and a crucial non-effect guarantee. Only limit/pagination behavior is left unexplained, a minor gap against an otherwise complete definition.

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 0% for two parameters, so the description must carry the load. It usefully implies what the query matches against (names, descriptions, skills), but says nothing about the limit parameter, its default behavior, or pagination.

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 public agent names, descriptions and skills") plus a summary of what comes back (profile/card URLs, repair_links). It does not, however, distinguish itself from siblings like list_agents or recommend_agents, which an agent could easily confuse this with.

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 clause "no task or probe is run" implicitly excludes verify_agent-style probing, which is useful routing. But there is no explicit when-to-use guidance relative to list_agents (enumerate everything) or recommend_agents (ranked suggestions), so the agent must infer which entry point to pick.

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