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

With no annotations, the description carries the full burden and delivers: 'Read-only,' 'Never returns tokens or keys,' and 'does not mutate memory.' It also discloses redaction behavior via the 'reason' enum and the cheap-probe relationship to 'health.'

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?

The description is dense but front-loaded with 'Seat-scoped memory diagnostic' and 'Read-only,' and every clause conveys a distinct fact (outputs, redaction, safety, health relationship). The length is justified by the number of status fields it needs to enumerate.

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?

Given an output schema exists and the one optional parameter is fully documented, the description covers the operation's purpose, safety, and key output semantics. An agent has enough to decide and invoke 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%, so the schema already documents 'repo' with optional workspace-slug semantics. The description doesn't add much parameter-specific detail beyond that, but it doesn't need to; 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 tool as a 'seat-scoped memory diagnostic' and enumerates its exact outputs, making the verb+resource clear. It also distinguishes itself from the sibling 'health' by stating it 'Complements service-level health' and is scoped to seat/memory rather than service-level.

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 description establishes when to use it: for inspecting seat-scoped memory state (bind, session, capture, queues) without mutation. It explicitly contrasts with service-level 'health' and notes it 'does not mutate memory,' though it doesn't enumerate all alternatives or hard exclusion conditions.

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