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

Annotations already mark destructive/readOnly false, but description adds substantial behavioral detail: safe default with SKIP-LIVE if CLI still running, kill_live's argv-anchored (not fuzzy) termination, side effects (queues ATTENTION_CLOSE_V1, parks FO session row), and write-tier approval mechanics (manager approval, from-now-on vs just-once, call on first clear ask). No contradiction with annotations; adds value beyond structured data.

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?

Description is front-loaded with purpose and trigger phrases, and every sentence adds information—trigger examples, mechanism, default, kill_live caveat, alternative sibling, approval note. Though longer than the minimal ideal, it packs dense, non-redundant guidance; the approval parenthetical is slightly unwieldy but necessary.

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?

Tool is destructive and has approval nuance; description covers purpose, usage, side effects, default behavior, kill_live semantics, and the write-tier approval flow. With full schema coverage and no output schema, an agent has what it needs to invoke correctly. Minor gaps like explicit handling of already-closed tabs are not critical given the schema's session_id sourcing note.

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 100%, so baseline is 3. Description adds real guidance on kill_live ('argv-anchored terminate, not fuzzy' and the trigger conditions for setting it true) and reinforces safe default behavior. Other params are already well-documented in schema, but the kill_live clarification is meaningful enough to raise to 4.

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 and resource ('Close an EXISTING coding tab on the operator machine for THIS operator') and explicitly distinguishes from sibling park_attention_sessions via the condition 'only the board is ghosty and the Terminal tab is already gone.' Trigger examples like 'close that session' and 'kill that Grok tab' make it unmistakable.

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?

Provides explicit trigger phrases, a condition for kill_live=true ('only when they say force-kill / stop it now'), and an alternative tool with the exact condition to prefer it ('Prefer park_attention_sessions when only the board is ghosty and the Terminal tab is already gone'). Also includes first-ask approval behavior and instructs not to re-ask in chat.

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