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

Goes well beyond readOnlyHint=true by disclosing the pagination contract: stable ordering guarantees no repeats or skips across pages, has_more signals continuation, and the offset schema documents cursor_expired failure behavior and opaque token handling. The sort_by note that unrecognized values are silently ignored is a non-obvious behavioral trait an agent must know to avoid misinterpreting results.

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 waste: the first front-loads purpose and capabilities, the second states the single most important behavioral guarantee (stable ordering preventing repeats/skips). Every clause earns its place, and the critical pagination contract is stated up front.

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 an 11-parameter read-only catalogue tool, the description plus a 91%-covered schema and an output schema cover the essentials: scope, filtering/sorting/pagination mechanics, cursor error semantics, and return-value shape via the output schema. The only minor gap is no direct statement of error behavior beyond cursor_expired, which the offset parameter documentation largely handles.

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 91%, so the baseline is 3 even though the tool description itself adds minimal parameter detail — it only frames offset/limit/has_more as the pagination mechanism. The heavy lifting is done by the exemplary schema descriptions (cursor token verbatim rules, integer-vs-string offset acceptance, business_id opacity and stability). The description adds no meaning beyond that, 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 — 'One business's service catalogue' — with explicit capabilities: filtering, sorting, and pagination. The scope qualifier 'One business's' distinguishes it from siblings like search_businesses (multi-business discovery) and compare_business_services (cross-business comparison), so an agent can select it correctly without opening the 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?

The 'One business's' scope clearly signals the selection condition: use this when a specific business is already identified. The `business` parameter description adds workflow guidance by routing the agent through search_businesses to obtain a business_id. However, there are no explicit exclusions or alternative routing (e.g., when to prefer compare_business_services), so it just misses the top bar.

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