lite

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

Annotations already disclose read-only behavior, open-world characteristics, and non-destructiveness. The description adds the practical constraint that the name must be exact and arguments must match the target schema, which is invocation guidance rather than deeper behavioral disclosure. Return format, error handling, and mismatch behavior are not covered, but annotations lower the burden.

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 concise sentences: the first states the action and scope, the second gives the exact invocation requirements. There is no filler or redundant restatement.

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?

The description supplies the essential discovery-to-call loop and invocation rules for a generic dispatcher. Since the tool has no fixed output schema, explaining return values is less necessary; however, it does not mention error behavior when an invalid name or malformed arguments are provided, which would slightly improve completeness.

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?

The schema already documents both parameters at 100% coverage, but the description adds meaningful provenance: `name` must be the exact tool name returned by `discover_tools`, and `arguments` must conform to that tool's input schema. This is more precise than the schema's generic descriptions.

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?

The description names a specific verb ('Run'), a specific resource ('Edge Thirteen tools returned by discover_tools'), and the delegation contract (exact name plus arguments object). This makes it immediately distinguishable from its sibling discover_tools, which has the discovery role.

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 description establishes the intended workflow: first discover tools, then call one by its exact name and schema-matching arguments. It does not explicitly state when not to use it or list alternatives, but the discovery-to-call relationship is clear enough.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, which the description does not contradict. The description adds valuable behavioral context beyond annotations, such as the workflow sequence and the alternate behavior of listing the catalog when no query is passed.

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 description is well-structured, front-loading the core purpose, then listing tool categories, and concluding with usage instructions. Every sentence adds value, with no redundant or filler content.

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?

The description covers the tool's purpose, usage, and next steps (calling call_tool). Given the lack of an output schema, it sufficiently explains what is returned (tool name and input schema). The limit parameter is self-explanatory, and the no-query behavior is disclosed.

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 each parameter is documented in the schema. The description adds meaning by explaining that omitting the query parameter lists the catalog, which goes beyond the schema's description of the query parameter. It also clarifies the purpose of the name parameter indirectly through the discovery workflow.

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?

The description clearly states the tool searches a catalog of 36 financial, compliance, and web-audit tools and returns input schemas. It differentiates from the sibling call_tool by explicitly describing the discovery-then-execute workflow ('Call this first... then call call_tool').

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?

Provides explicit usage instructions: 'Call this first with a plain-English description of the task' and 'then call call_tool with the name it returns.' Also clarifies the no-query behavior for listing the catalog, leaving no ambiguity about when and how to use the tool.

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