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

The description reveals the non-obvious cost (15 credits), the output's nature (model-ranked rather than frequency-based), and the practical consequence that fetch_markdown is cheaper if the agent will do its own reasoning. These go beyond the annotations, which only indicate idempotency and non-read-only behavior; there is no contradiction with readOnlyHint=false.

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 short, front-loaded sentences: endpoint, output/quality, cost, and the decision-relevant comparison. Every sentence adds value and no space is wasted on repeating schema 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?

For a 9-parameter tool with no output schema, the description covers the crucial selection facts: what the result looks like, how much it costs, and when to use a cheaper sibling. The full parameter details live in the schema, so nothing essential to correct invocation is missing, though a bit more detail on the result structure would have been useful.

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 100%, so every parameter already carries a meaningful description. The tool description adds no parameter-specific semantics beyond the schema, which is acceptable and earns the baseline for high coverage.

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 names the exact endpoint (POST /keywords) and the concrete output: 5–15 terms/phrases best representing the page, ordered by relevance. It also distinguishes the tool from siblings by noting that the ranking comes from a language model, not raw frequency, and by referencing fetch_markdown and summarize_page.

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?

It gives explicit guidance for a key alternative: if the agent will reason over the content itself, fetch_markdown at 1 credit is the better choice, while extract_keywords is positioned as the way to get a pre-digested keyword list. It does not, however, spell out when to pick extract_keywords over summarize_page or extract_metadata, so the routing guidance is strong but not exhaustive.

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