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

Annotations already declare the safe-read profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add behavioral context beyond that. It does: flagging the headline metric as a MODELLED value per referral is a meaningful caveat, and it discloses that results are ranked best-first and paginated. Permission or rate-limit behavior is not discussed, keeping 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?

Three sentences, zero filler: purpose and scope first, then concrete usage triggers, then return shape. Every clause carries information and nothing is repeated from the schema.

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 nine-parameter search tool with no output schema, the description covers what matters: what is searched, how results are ranked and paginated, and what a 'value' actually represents. Safety profile is fully carried by the annotations, so nothing an agent needs before calling is missing.

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 100%, so the schema already documents every parameter and the baseline is 3. The description adds only marginal meaning ('compared by network, commission, cookie window, and a modelled value') to explain what the default 'value' sort measures. It does not resolve the one ambiguity the schema leaves open, namely what the 'network' value in the confidence enum means.

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?

Names a specific verb and resource ('Search and filter the directory of affiliate programs') and even states the comparison axes and return shape ('ranked, paginated list of full program records'). The plural directory scope implicitly contrasts with the single-record get_affiliate_program sibling, but no sibling is named in the description itself, so it falls short of explicit differentiation.

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 concrete trigger questions ('best/highest-paying affiliate programs for X') and enumerates the supported filter modes: category, network, recurring vs one-time, minimum value. There are no explicit when-not conditions or routing to list_networks/list_categories inside the description (those only appear in the parameter schema), so it is clear context without exclusions.

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