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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), it discloses non-obvious workflow behavior: URL input starts background extraction, a card solicits the website when status is missing, no separate chat reply should be sent while waiting, and skip/added actions are already persisted. These are substantive side-effect and timing disclosures annotations cannot carry.

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 purpose is front-loaded in the first sentence and subsequent sentences are operationally load-bearing (exclusions, card flow, status gating). It is a dense wall of text, but nearly every clause earns its place; only minor consolidation is possible.

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?

An output schema exists, so return values need not be explained. Given the conditional/stateful nature of this tool, the description covers triggers, exclusions, duplicate-call protection, waiting behavior, and the ownership rule, which is everything an agent needs to call 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 description coverage is 100%, so the baseline is 3, but the description adds real meaning: it maps the conditional usage of websiteUrl (only when the user types it in chat) and skip (only on explicit decline), and warns that cardId is never set by the caller. This goes beyond the schema's own field descriptions without contradicting them.

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 ('Save the user's own website for the workspace') and immediately scopes it against siblings by naming check_website as the tool for verification. It further disambiguates ownership ('Use the user's own site, never a client's site'), so an agent can distinguish it from check_website and the document/proposal siblings without opening any schema.

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?

Gives explicit triggering conditions (user types the website -> websiteUrl; user declines -> skip: true), explicit exclusions ('never call it just to check'), and duplicate-call prevention ('If the user says they added or skipped it in the card, it is already saved: do not call this again'). It also specifies the required pre-state (status must be has_website, started, skipped, or not_needed) before proceeding.

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