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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), and the description adds real behavioral context beyond them: results carry a time-precision qualifier ('how precisely HEY knows its time'), the response is paged, and pagination is driven by the before cursor. It does not cover ordering or behavior when a slug is unknown, so it stops short of 5.

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 core question, then event coverage, then lens/pagination mechanics — a sensible information order with no filler sentences. It is dense but every clause carries content; the phrasing around HEY's time precision is slightly awkward but not wasteful.

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 an output schema present, the description need not explain return values, and it doesn't. For a 4-parameter, read-only, paged read tool it covers the essentials: scope, event types, lens selection, and pagination. Minor gaps (ordering, empty/unknown-slug behavior) are not blocking for correct invocation.

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 75%, so the schema already documents slug, limit and before. The description still adds value by naming the four lens values and flagging build as the default (which the enum cannot express) and by explaining that before is a cursor from a previous answer, not an arbitrary timestamp. Limit semantics 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 outcome (what a project shipped and when) and enumerates the event classes it covers — builds, releases, code, contract deploys, upgrades, interface changes, token verification, locks/unlocks. An agent can tell it is a project-scoped timeline tool. It does not differentiate itself from siblings like get_changes or get_contract, which is the only thing keeping it from 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 leading question implies the use case (reconstructing a project's shipping history), and the lens list hints at how to narrow scope, but there is no explicit when-to-use versus get_changes, get_contract, or get_evidence, and no stated preconditions. Usage is inferable rather than stated.

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