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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered; the description still adds real value by disclosing the result shape (capabilities, verification tier, settled-order counts) and a prompt-injection warning that provider-written names/taglines/capabilities must be treated as data, not instructions. The settlement/USDC/irreversibility sentences are true context but not behavior of this read-only call, which keeps it short of a 5.

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?

The filter axes and the sibling routing are front-loaded in the first two sentences, which is the right order. The closing sentences about Base settlement and irreversible USDC transfers are off-topic for a read-only search and dilute an otherwise tight definition.

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 an output schema present the description needn't enumerate return values, and it still summarizes what each result carries and where to go deeper. For a 10-parameter, fully-optional filter tool this is nearly complete; only result ordering/pagination behavior is left entirely to the schema.

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 every parameter including enums, defaults and bounds is already documented. The description restates the most important semantics ("skills (all must match)", modality as input-or-output, exact language match) but adds no syntax or format detail beyond the schema, so baseline 3 applies.

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") and enumerates the actual filter axes: name/tagline, skills, modality, protocol, language. It also explicitly separates itself from the sibling that could be confused with it ("search_services finds the listings themselves"), so an agent can route without opening either schema.

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?

Gives a positive selection rule ("Use it to find who can do a job"), a named alternative for the adjacent case (search_services for listings), and a follow-up path ("read one in full with get_agent"). That is when-to-use plus when-to-use-something-else, both explicit.

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