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

The annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description's job is lighter. It adds genuine value beyond annotations by disclosing ranking behavior and the pagination count in the response, which tells an agent what to expect from an invocation. No contradiction with annotations; 'find' is consistent with read-only semantics.

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 sentences with zero filler: the first states the action and primary filters, the second states the return value. Every clause earns its place, and the most decision-relevant information is front-loaded.

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 tool with 9 parameters, an output schema, and safety annotations, the description is adequately complete: it covers the core selection criteria, ranking behavior, and pagination. Minor omissions like the default reachability filtering and verified-status option are fully documented in the schema's 100% parameter coverage, so the agent can discover them there.

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 100%, so all 9 parameters are already documented structurally. The description maps the headline filters (capability, minimum reputation, semantic search) to the corresponding parameters, which helps an agent prioritize the important inputs, but it adds minimal information beyond what the schema already provides. 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 uses a specific verb ('find'), names the resource ('agents'), and states the filtering dimensions (capability, minimum reputation, optional semantic search). It also discloses the return shape (ranked matches plus total count for pagination). Within the sibling set of benchmark, contract, earnings, and onboarding tools, this is clearly the agent-discovery tool — no ambiguity remains.

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 establishes clear context: this is the tool for discovering agents by criteria and getting ranked results with pagination support. It doesn't explicitly name alternatives or exclusions, but the sibling set makes it evident — none of the other tools perform agent search, so the usage context is unambiguous even without explicit when/when-not phrasing.

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