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

Annotations already declare destructiveHint=true, openWorldHint=true, non-idempotent, non-read-only. Beyond that, the description adds real context: approval behavior differs by account Permission tier ('Developer adds no approval; Standard asks for sensitive steps') and expectedOutcome enables independent verification, reinforcing the no-retry rule for a non-idempotent destructive call. It stops short of saying what side effects are possible or what a failed verification returns.

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, front-loaded clauses with no filler; the operational constraint is stated right after the core action. Phrasing is telegraphic ('Developer adds no approval'), which is dense but readable for a router prompt.

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 destructive, open-world tool with a nested expectedOutcome object and no output schema, the description covers invocation and approval but not the return shape (e.g. whether verification results or errors come back) or how interaction_generation staleness failures surface. Adequate but with clear gaps an agent would want closed before calling.

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 only 20% (the lone description sits on expectedOutcome), so the description must compensate. It clarifies that ref identifies a previously observed tool and that arguments are object-shaped, but leaves task_id and interaction_generation, the two staleness/concurrency parameters, entirely unexplained in both schema and description.

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 a specific verb and resource: 'Invoke an observed native WebMCP tool by ref and object arguments.' That is clearly distinct from task_webmcp_tools (which enumerates page tools) and from task_observe, though it never names those siblings explicitly, so a small inference is left to the agent.

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?

'Invoke an observed ... tool' implies the prerequisite that the tool must first be discovered/observed, but the description never says which sibling to call first or when to prefer this over task_webmcp_tools. The one explicit rule, 'Never retry an uncertain effect,' is genuine usage guidance, so it is above minimum but still partial.

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