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

Annotations already declare readOnlyHint=true, non-destructive and closed-world, so safety is covered; the description adds valuable orchestration behavior — the result must not be resolved by prompting the user or by calling set_website, because create_proposal's card handles website capture and document creation. It doesn't describe the status values returned (e.g., what 'missing' vs present look like), though an output schema exists to cover that.

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-loads the purpose, then gives timing and the branching rule for a missing status. Dense but every clause carries an actionable instruction; the final clause about the card creating the document is slightly compressed but still parses.

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 parameterless read check with annotations and an output schema, the description covers the critical agent-facing decisions: when to call, what to do for each status, and which sibling not to call. Only the enumeration of status values is left to the output schema, which is appropriate.

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?

Zero parameters, so there is nothing to document; baseline 4 applies. The description doesn't need to explain inputs and correctly spends its space on call sequencing instead.

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 states a specific check: whether the workspace has the user's own website. It does not explicitly contrast with sibling get_profile or set_website, though the 'do not call set_website' instruction implies the distinction. An agent can tell what it queries, but the differentiation from get_profile (which might also expose a website) is left implicit.

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?

Explicit sequencing (after initialize_chat, before drafting each new document) and explicit negative guidance: if status is missing, don't ask in chat and don't call set_website, instead rely on create_proposal's card. It names the alternative path and the condition that selects it.

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