vision_advice

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

Annotations already establish read-only and idempotent behavior, and the description adds a genuinely useful caveat: only `no_text_layer` is currently measured, while `low_confidence_table` and `figure` are always false. It does not mention cost or whether pages are rendered, which would be nice but is secondary.

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?

Front-loaded with the core question and tight overall. It spends a few lines explaining output fields that the output schema already covers, which is slightly redundant but does convey the caveat that two of the reasons are stubs.

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 single-parameter read-only tool with an output schema, the description supplies what is missing: parameter format, what 'needs_vision' means, and the current measurement limitation. Only the absence of routing guidance against sibling extraction tools keeps it from being fully complete.

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 must carry the parameter — and it does, specifying that `path` is an absolute path on the local machine, which prevents relative-path or URL attempts.

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 purpose: identify which pages of a local PDF warrant a vision model, and why. It is clearly an analysis/advisory operation, distinct from the extract_* siblings, though it never names them explicitly.

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?

Usage is implied — call it when deciding whether to route pages to a vision model — but there is no explicit when-to-use/when-not guidance or reference to alternative tools such as extract_text or extract_tables that might already cover a page.

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