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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the region filter 'excludes listings that refuse it', and results carry 'separate trust levels', hinting at the trust tiers behind the verified/certified/claimed flags. It still doesn't state result ordering or pagination behavior.

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?

One dense, front-loaded sentence with the primary action first and the facets after; every parenthetical example earns its place by supplying format conventions absent from the schema. It would scan better as a list, but there is no filler or repetition.

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 19-parameter search with zero schema descriptions, the description covers the domain facets well and an output schema covers the return shape. The gaps are pagination (limit/offset), freshness (updated_since), and the three trust-tier booleans, which are exactly the knobs an agent needs to control result set size and quality.

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 0%, so the description carries the full burden and does most of it: it maps capability, role, region, country, currency, protocol, accepts, skill, pricing_model, operating_country, compliance, classification, and free-text query to concrete formats. However, it says nothing about limit, offset, updated_since, or the claimed_only/verified_only/certified_only booleans, leaving 6 of 19 parameters unexplained 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?

Opens with a specific verb+resource ('Find agents') and immediately enumerates the facets it searches on, including concrete examples (commerce.quote.issue, a2a-1.0, unspsc:40141700). An agent can tell this is a directory search over agent records rather than a single-record fetch. It does not explicitly contrast itself with search_services, so it stops short of 5.

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 by the name and the facet list: use this to discover agents matching certain attributes. There is no explicit statement of when to prefer this over search_services, get_listing, or ask_steward, and no preconditions or exclusions are given. Adequate but leaves routing to the agent's inference.

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