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

Annotations already carry readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds genuinely useful behavioral context beyond that: it discloses persistence ('persist the summary'), the full processing pipeline, and the auto-selected token-budget view (L0/L1/L2). No contradiction with annotations; the 'stop' mutation aligns with readOnlyHint=false and idempotentHint=true is plausible for a stop-and-analyze.

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 purpose, then cleanly structured into Parameters and Returns sections with headers. The pipeline enumeration (parse → normalise → threshold → fingerprint → cluster → rank) adds slight verbosity but each element earns its place by clarifying behavior. No wasted sentences.

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?

Moderately complex tool (3 params, multi-stage pipeline, summary output) with no output schema, so the Returns section is the only source for return info. It explains counts and a formatted summary plus a drill-down pointer. Minor gap: the exact summary structure isn't specified, but the lifecycle pointer and full parameter documentation make it adequate 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 description coverage is 0%, so the description carries the full burden and fully compensates. All three parameters are documented with real semantics: sessionId tied to the hang-start session, topN with its default of 3, and budgetTokens explained as a size cap that selects L0/L1/L2. Every parameter is meaningfully covered despite the empty 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 verb chain ('Stop... parse... persist... return') with an explicit resource (HangBuster session). The clustering pipeline is enumerated, and it clearly distinguishes from siblings by referencing hang-start as the origin and hang-get-details as the follow-up. An agent can tell exactly what this does without opening the schema.

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?

Establishes the lifecycle context ('the session from hang-start') and gives an explicit post-call pointer ('Drill deeper with hang-get-details'). It doesn't spell out explicit when-not-to-use conditions or alternative selection rules, but the lifecycle framing plus sibling pointer provides clear contextual guidance.

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