invoke_read_tool

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

Annotations already declare readOnlyHint=true, and the description adds real value on top: it refuses write tools, requires an exact name, and forwards arguments to the target. It does not say what happens on an unknown or rejected tool name, nor whether the response is the raw target output or a wrapper — a moderate gap for a dispatcher.

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, front-loaded with the core action, and each clause carries information: the read-only constraint, the name pattern, the discovery source, the alternative, and the refusal rule. No filler.

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 no output schema, the description never indicates what is returned — the target tool's payload verbatim, a wrapped result, or an error envelope on refusal. For a dispatcher whose whole job is relaying another tool's invocation, that return-shape gap is meaningful even though the safety profile is fully covered by annotations.

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% and both parameters are documented, including that arguments must match the tool's input schema, so the description adds little beyond restating 'exact name' and 'with its arguments'. The nested, opaque arguments object would benefit from an example or a note on pass-through behavior, which is absent.

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 (run/invoke) and resource (a READ-ONLY WebCake tool by exact name), and names the naming pattern (list_*/get_*/search_*/count_*) plus the authoritative signal (annotations.readOnlyHint in search_tools). It explicitly distinguishes itself from the sibling invoke_tool, so an agent can differentiate 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?

"Prefer this over invoke_tool for lookups" gives an explicit alternative and selection condition, and "Refuses tools that change data" states a hard exclusion. What's only implied is the workflow prerequisite of calling search_tools first to obtain the exact name — the parenthetical hints at it but never spells out the sequence.

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