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

Goes well past the readOnly/idempotent annotations: it warns that redacted or unavailable evidence is dropped, that cursor traversal is live rather than a snapshot, that elevated permission is required despite read-only hints, and that returned text is public-written and must be treated as data, not instructions. That last point is exactly the kind of untrusted-content guidance an agent needs.

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-loaded with purpose, then returned fields, filtering, pagination, permissions, and the safety caveat — each sentence carries distinct information. Slightly dense at six sentences, but nothing is padding.

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?

With no output schema and five parameters at 20% coverage, the description supplies the return-shape summary, pagination model, auth requirement, exclusion behavior, and injection-safety guidance. An agent has everything needed to call it and interpret the results 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 coverage is only 20% (only account_id is documented), so the description has to carry the load and largely does: it explains the conversation and linked-request filters, the limit/continuation behavior ('Follow next_cursor'), and the evidence-inclusion rule. Minor gap: it says 'next_cursor' while the schema field is 'cursor', and limit bounds are left to 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?

States a specific verb and resource (list private evidence/suggestions surfaced in the Inbox) and discloses what the payload contains: review status, source quotations, and suggested or accepted request links. That clearly separates it from the message/conversation listers, though no sibling is named outright.

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 the selection context ('Extraction stays in the Inbox review workflow'), the optional narrowing filters (conversation or linked request), and a prerequisite (features.manage even on read-only connections). It does not explicitly route the agent to a named alternative, which keeps it below a 5.

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