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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds two behavioral facts beyond annotations: the conservative gating logic (stale success plus multiple independent failed probes) and a per-call cost of 0.003 USDC. It lacks details on auth, rate limits, or what happens when conditions are not met.

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 a single semicolon-joined sentence with no wasted words, but it front-loads the condition rather than the action. Its terse, under-specified style leaves important gaps, so it is concise but not optimally structured for an agent.

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 detector that takes a nested policy object, has no output schema, and has 0% schema description coverage, the description omits what the policy object contains, what the output looks like, and how the classification is returned. It provides only cost and a high-level condition, which is insufficient for confident 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 description coverage is 0%, and there are two required nested parameters. The description partially maps conditions to the 'tool' object's fields ('stale success' → last_success_at, 'multiple independent failed probes' → independent_probe_count/reachable), but it says nothing about the required 'policy' object, leaving half the parameters undocumented.

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 indicates the tool classifies likely abandonment but does so indirectly through a condition ('Require stale success plus multiple independent failed probes before classifying...') rather than a direct verb like 'detects' or 'classifies'. It does not differentiate from siblings such as tool_capability_drift_monitor. The pricing detail ('0.003 USDC') is not purpose-related.

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?

No explicit when-to-use or when-not-to-use guidance is given. The conditional phrasing describes internal logic, not invocation context, and no alternative tools are named. The agent must infer that this is for abandonment classification.

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