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

readOnlyHint=true already tells the agent this is a safe read, so the description's job is to add operational context beyond safety, and it does deliver the incremental-fetch contract plus the 0-means-all convention and the next_since cursor. It does not describe event payload shape, ordering, or any cap on how many events a poll returns. With annotations covering the safety profile, a 3 reflects useful but incomplete added context.

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?

Two short sentences, zero filler, with the scope of the call front-loaded and the pagination continuation placed second. Every clause carries information the agent needs to call this correctly in a loop.

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 should carry the return-value burden, and it only tells the agent about next_since while saying nothing about what an event looks like or whether the feed is ordered or bounded. For a polling primitive that is a meaningful gap but not a blocking one, since the core call contract is clear.

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 67% and the undocumented parameter is `since`, which the description explicitly explains as a unix time where 0 returns everything. It also introduces next_since, a value the agent only learns about from this text since there is no output schema. That is genuine meaning added beyond the structured fields, though the format of `secret` is left entirely 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?

The description states a specific resource (a mandate's recorded events) and a scope (since a unix time, 0 = all), so an agent can tell this is an incremental event feed rather than a status lookup. The wording 'Events a mandate recorded' is slightly compressed but unambiguous. It does not explicitly contrast with mandate_status or mandate_signal, keeping it below a 5.

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?

The second sentence gives real operational guidance for the polling loop: feed the returned next_since into the next call. That is useful implied usage, but there is no statement of when to choose this over mandate_status or mandate_signal, nor any note on stopping conditions or whether 0 should be used only on first poll.

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