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

Adds real behavior beyond the annotations: pages are bounded, results carry no ranking, no cards are auto-rendered, pages cannot prove relevance or availability, and there is no zone dimension. However, the annotations declare readOnlyHint=false while the description frames the call purely as a 'Read', and it never explains what non-read-only effect occurs (e.g., scenario/call-budget accounting). That leaves an important behavioral trait undisclosed.

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?

Purpose is correctly front-loaded in the opening clause. But the body becomes a dense run-on of workflow policy and internal jargon ('structured read', 'justified descriptive fallback', 'eight total MCP calls per scenario, including resolution, checks and the final render') that is slow to parse and mixes catalog behavior with multi-tool orchestration rules.

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, return values need not be described, and the definition still covers scope, paging, filtering semantics, the no-zone limitation, and the required follow-up render step. The remaining shortfall is the unexplained readOnlyHint=false and the unbound 'fallback' terminology, but nothing critical for correct invocation 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 0%, so the description has to carry the parameters, and it does for the key ones: categoryUuid 'filters services by the existing taxonomy' and should be omitted for standalone classes, tying kind to categoryUuid; presentationLocale es/en should be chosen 'from conversation or user preference'. Page/limit are only covered indirectly by 'bounded pages', with no guidance on paging strategy or page size, so it stops short of full compensation.

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 concrete verb and resource ('Read current public Costa Rica services or classes in bounded pages') plus explicit scope (public, Costa Rica, paginated). The negatives ('without search or relevance ranking or automatic cards') distinguish it from wellfred_search_services, wellfred_search_classes and wellfred_render_services. An agent can select it against its siblings without opening any 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 explicit routing: catalog has no zone filter, so zone comparisons must go through search with returned geography IDs, and the final selection must go to wellfred_render_services once. It also caps effort ('one structured read and at most one justified descriptive fallback', 'eight total MCP calls per scenario'). The only gap is that 'structured read' and 'descriptive fallback' are not tied to specific sibling tool names, leaving the agent to infer which siblings those are.

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