percollate_read_md

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

With no annotations, the description carries the full behavioral burden, and it does disclose a genuinely useful trait: results are cached locally and repeat calls for the same URL return instantly. However, it says nothing about failure modes an agent should anticipate - paywalls, auth walls, JS-rendered pages, cache invalidation, timeouts, or rate limiting.

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?

Three tight sentences, front-loaded with the core action, then the mechanics, then the intended use case. No filler or redundancy.

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, and the description compensates by stating exactly what is returned ('the full Markdown content') plus the caching lifecycle. For a single-required-param read tool with a fully described schema, an agent has what it needs to invoke it correctly.

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 all ten parameters (css, style, template, wait, debug, no_amp, hyphenate, title, author, url) are already documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 verb+resource ('Read a web page as Markdown') and describes the concrete pipeline: fetch, convert, cache, return content. It implicitly separates itself from the percollate_download_* siblings by emphasizing 'returns the full Markdown content' and in-conversation consumption, but it never names a sibling to make the distinction explicit.

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?

'Ideal for consuming web content directly in conversation' hints at when to reach for this over the download_* variants, which is implied usage rather than stated guidance. There is no explicit when-to-use/when-not statement, no mention of the alternative download tools, and no prerequisites.

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