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

The description's 'Read' language aligns with the readOnlyHint and destructiveHint:false annotations, confirming a non-destructive operation. It adds useful behavioral context about returning passages rather than full content, though the annotations already cover the key safety aspects.

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 two sentences, front-loads the purpose, and immediately follows with actionable selection guidance. There is no redundant or extraneous 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 core purpose and usage context well, but with no parameter descriptions and zero schema coverage, the optional pagination/limit parameters remain under-specified. The output schema is present but not detailed in the description, so the tool is not fully self-contained for an agent needing parameter semantics.

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 description coverage is 0%, and the description does not explain the optional parameters cursor, max_tokens, or max_passages beyond their names. While url and query are implicitly clear from the description, the optional parameters' semantics are left entirely to inference.

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 reads a public article or YouTube URL and returns only relevant passages, with specific output details about anchoring and section labels. It also explicitly differentiates itself from get_article by focusing on targeted queries rather than full retrieval.

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 gives direct usage guidance: 'Use this instead of get_article whenever you have a specific question about a link' and explains the benefit of lower token usage. This makes the selection criteria between search_article and get_article explicit.

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