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

With no annotations, the description carries the full burden and does well: it discloses that pausing is irreversible ('never restores auto-funding'), that only future authenticated events are imported, that there is no backfill, and that no publication/funding/work starts. It also names the API-key auth requirement. Missing only error/failure behavior and idempotency.

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?

Four tight sentences with the authorization precondition and the destructive 'pause' caveat front-loaded. No filler, though the sentence announcing the API-key requirement could be merged or placed earlier.

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 mutation tool with no annotations, no output schema, and two undocumented required parameters, the description covers side effects and safety well but leaves two agent-critical gaps: how to source config_id and what the call returns on success or failure.

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 0%, so the description must compensate. It does partially: 'Sentry or Linear connection' maps config_id to a connection and the replace/pause wording maps to the radar/paused enum. However, it never explains how to obtain a config_id (UUID) or that the enum corresponds to mode.

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 specific verbs (replace/pause) and a specific resource (a Sentry or Linear connection's Autopilot dispatch vs. private radar intake). It is distinguishable from the sibling list_work_radar_sources, which reads rather than mutates, though the branded jargon ('Autopilot dispatch', 'private radar intake') assumes prior context.

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 precondition ('with your operator's explicit authorization') and clarifies what pausing does not do, which implies when to choose the 'paused' mode. But it never states when to use this tool versus alternatives (e.g., where to get config_id, presumably list_work_radar_sources) or when not to call it.

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