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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine value with result ordering (newest first), deduplication of copies, and the fact that per-service check status is reported. It stops short of describing pagination behavior or what fields each entry contains.

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?

Three short sentences, no filler, and the core purpose is front-loaded ahead of result-shape and sibling routing. Every clause contributes information an agent needs.

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 7-parameter, no-output-schema search tool, the description conveys scope, ordering, deduplication, and what the check-status field means. Pagination exists only via the cursor parameter's schema text, so a brief note on paging would close the remaining gap.

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?

With 86% schema description coverage, the schema already documents chain, money, query, service, working_only and cursor in detail. The description adds only indirect context by mentioning that service types pass "lcas's last check," which loosely maps to working_only. Baseline 3 is appropriate when the schema carries the parameter semantics.

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 lcas directory of ERC-8004 agents") and immediately characterizes the result ordering and grouping. It also names the sibling get_agent as the path to full details, so an agent can tell the two apart without opening schemas.

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 routes deep-detail lookups to get_agent, giving a clear alternative for one common case. It does not address when to use this versus directory_status, nor does it say when listing (omitting query) is preferable to querying, so the guidance is clear but not exhaustive.

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