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

With no annotations provided, the description must disclose behavioral traits. It only hints at behavior with 'semantic' and 'top-k', suggesting embedding-based retrieval and limited results, but it does not state read-only guarantees, return format, sorting behavior, or any side effects. The description fails to convey important operational details.

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 extremely concise at one short phrase, but it is under-specified rather than efficiently structured. It lacks the necessary detail to stand alone, making it inadequate for an agent. The brevity does not compensate for missing essential information.

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?

There is no output schema, so the description should explain the return value. 'top-k' implies the results are limited to k items, but it does not specify whether the output is the original documents, scores, or something else. Given the three parameters and no additional context, the description is incomplete for practical use.

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 needed to compensate. It adds some meaning by mentioning 'top-k', which relates to the top_k parameter, but it does not clarify the 'query' or 'documents' parameters. The description provides minimal insight beyond what the schema already shows from parameter names.

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 'Semantic retrieval top-k' conveys a vague purpose: it indicates a semantic search that returns the top-k results. However, it does not specify the source or what is being retrieved (e.g., documents from a provided list), making it distinguishable from siblings only through the 'semantic' qualifier. It is not a tautology because it adds meaningful terms, but it lacks a clear verb+resource structure.

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?

No guidance is given on when to use this tool versus alternatives. It does not mention that it operates on a provided list of documents, nor does it exclude cases like memory_search or web_search. The description is silent on use cases, prerequisites, or when not 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.