Rescan Documentation

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

The description discloses that the tool flushes caches and reloads multiple data sources, which is useful side-effect transparency. However, with no annotations and no stated consequences (e.g., whether this is disruptive, requires permissions, or how long it takes), the behavioral description is incomplete.

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 a single, focused sentence with concrete technical terms and no filler. It front-loads the key verb phrase 'Flush caches and reload' and lists the exact resources affected.

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 parameterless refresh operation, the description covers what and how, but it does not say when to use it (e.g., after documentation source changes) or what side effects/return behavior to expect. The output schema could help but is not described. This leaves some operational ambiguity for an agent deciding whether to call it.

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 tool has no parameters decorating the schema, so there is no ambiguity about inputs. A baseline of no parameters means the description needs no additional parameter explanation, and it correctly omits any.

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 states the specific operation ('flush caches and reload all OpenWebNet specifications, markdown documents, and codebase AST models'). The verb is concrete and the resource scope is explicit, making the tool's purpose immediately distinguishable from the read-only siblings like search_documentation and get_who_spec.

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 implies this is a maintenance/refresh action rather than a query operation, but it never states when to invoke it, when not to, or how it relates to alternatives. Unlike examples such as 'use search_calls_extensive instead', there is no explicit routing guidance.

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