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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral constraints—'No input form or execution' and 'Never fabricate request IDs or terms'—but does not explain how the digest is produced or what the presentation token represents.

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 description is short and front-loads the read-only digest concept, but the second clause is grammatically fragmented ('agents from the exact Search presentation token, or a current owner-bound thread approval...'), making it harder to parse. The meta-sentence 'The assistant handles all decisions and subsequent tools' is low-value and interrupts the actionable guidance.

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 tool with three oneOf variants and no output schema, the description leaves critical context unstated: what a 'Darwin view' actually returns, where the presentation token originates, and how the agent should decide between the three variant kinds. The annotations cover safety, but they cannot compensate for the missing invocation semantics.

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?

The schema has complete structural coverage (oneOf variants, enums, required fields), establishing a baseline of 3. The description mentions the kinds of items (agents, approval, authentication, payment, output) but does not clarify how to choose a kind, where a presentationToken comes from, or what thread/request/message mean, so it adds little beyond the schema.

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 identifies the resource as an 'Optional read-only digest' covering agents, approvals, authentication, payment terms, or output, which gives a rough sense of scope. However, the phrasing is fragmented and relies on opaque terms like 'Darwin view' and 'Search presentation token', so an agent cannot crisply state what the tool returns or how it differs from siblings such as open_darwin or search.

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 exclusions: 'Never use for clarification, no-match, ordinary chat, progress or acknowledgements,' which meaningfully narrows the invocation context. It does not name alternative tools for the excluded cases, but the when-not guidance is clear enough to prevent most misuse.

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