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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real context beyond them: the admission prerequisite and the fact that the response is scoped to a minimum working set rather than a full event log, which sets expectations about payload size and content.

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?

Three short fragments with the gating prerequisite front-loaded in brackets. Nothing is wasted, though the telegraphic style ('Minimum working context, followed by the primary actor result') costs some clarity relative to its brevity.

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?

For a two-parameter read tool with no output schema, the description covers the prerequisite, the safety profile (via annotations), and roughly what is returned. The exact shape of 'primary actor result' remains undefined, but that is a minor gap at this complexity.

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%, so both parameters are already documented in the schema. The description adds nothing about actor_token or matter_id beyond implicitly pointing at the enrollment flow, so the baseline 3 applies.

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 the resource ('working context') and hints at the return ('followed by the primary actor result'), but 'minimum working context' is jargon that doesn't tell an agent concretely what data comes back. The exclusion 'Not the event log' does differentiate it from a sibling, which lifts it above pure vagueness.

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 states an explicit precondition sequence (enroll, then atlas.bind_actor), which is genuinely useful routing information. However, it doesn't say when to call this instead of related reads such as atlas.get_matter, atlas.institutional_view, or atlas.discover – only the admission gate is covered.

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