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

The key disclosure — that the call 'Marks them as seen unless mark_seen is false' — explains why readOnlyHint is false despite this looking like a read, which annotations alone cannot convey. It still doesn't say what 'seen' means for the feed afterwards or what an empty result implies, but the side effect and its off-switch are stated.

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 the since-last-check scope, then the enumerated payload, then the side effect and the use-case trigger. Dense but every clause carries information; the parenthetical about signed name and extras earns its space as return-shape detail.

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?

No output schema exists, so enumerating what the activity contains (opened, accepted with signed name/extras/total, questions, declined) is doing real work. Combined with the since-last-check framing and the seen-marking behavior, an agent can invoke this correctly; only ordering/emptiness edge cases are unstated.

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 50%: trade_key is documented in-schema but mark_seen is not. The description compensates by explaining mark_seen's effect and that its false value preserves the unseen state, though it leaves the default (true) implicit.

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 concrete resource and a delta-scoped purpose: customer actions on quotes 'since the trade last checked,' enumerated as opened, accepted, questions, declined. That is clearly distinct from list_quotes or get_quote, which return quote records rather than a since-last-check activity feed, though no sibling is named explicitly.

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 a strong situational cue ('Answers when the trade asks "any news on my quotes?"') that tells the agent the right conversational moment, but it never states when to prefer get_quote/list_quotes instead, nor what to do if the user wants full detail rather than a delta.

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