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

Beyond the readOnlyHint and destructiveHint=false annotations, it discloses meaningful behavior: no account is read, the pass token names the request, results come in PolicyVera's order, message bodies and prices and personal details are excluded, and new-content filtering is driven by the since timestamp. The closing-scope limit ('Works until the request closes') is exactly the kind of operational context 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?

Dense, front-loaded, and free of filler, with the core read stated first and exclusions last. The heavy use of parentheticals and stacked clauses makes it harder to parse than necessary, but every clause carries information.

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, the description carries the return-value burden and does so: agent names, per-agent status, message-sent flag, ordering, and explicit exclusions of prices, message text and personal details. It also explains the incremental-refresh pattern via since, which is what 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 coverage is 100% and both parameters already document their origin and semantics, so the description mostly restates them. It does add the framing that the statusToken is a 'pass' naming the request and that no account is read, which slightly clarifies trust boundaries, but it adds no format or edge-case detail 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?

States a specific verb and resource ('Reads one request's progress') scoped by its statusToken origin in send_quote_request, and enumerates what the read yields: each agent by name with quoted, declined or still-working state and whether a message was sent. This clearly separates it from siblings like check_quotes and read_messages, which read the actual content.

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 key conditional guidance: pass since (the previous check's checkedAt) so only new activity is listed, and points to check_quotes and read_messages for signed-in reading of a quote or message. It also bounds the tool's lifetime ('Works until the request closes') but does not explicitly state when not to use it versus preview_quote_request.

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