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

Adds substantial context beyond annotations: it costs no credits but counts toward a daily URL-analysis quota, it creates/mutates a draft project (consistent with readOnlyHint=false), and it is asynchronous, requiring polling. The quota and async-polling disclosures are exactly the kind of behavior an agent cannot infer from the annotation block.

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?

Four short sentences, front-loaded with the cost/quota note, then the action, then the required follow-up, then the alternative. No sentence is filler.

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 async workflow is covered, but with no output schema the description never says what analyze_url returns (job id, project id, or status) or how to identify which project to poll. For an async mutation tool that is a meaningful gap in an otherwise strong definition.

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 only 33% — project_id is described in the schema, while url (required) and language have no descriptions at all. The description clarifies that project_id defaults to a new draft project, but never mentions the language parameter or its effect, leaving one of three parameters completely opaque to the caller.

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 (starts reading a website) and resource, and enumerates exactly what gets extracted (screenshots, colors, fonts, logo, copy). It distinguishes itself from siblings by naming get_project (polling) and create_project (which already does this with a url).

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?

Explicitly routes the agent: it says to poll get_project until analysis_status is ready, and that create_project with a url already performs this analysis, implying this tool is for the standalone/into-existing-project path. Both the follow-up tool and the overlapping alternative are named.

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