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

Annotations only say destructive/non-idempotent. The description goes beyond: side effect ('Queues a sticky for the desk launcher'), prerequisite ('host must run attention-launcher'), per-host behavior (factory/CASCADE refuse Terminal; grok opens Grok Build Terminal, etc.), and write-tier approval semantics. No contradiction with annotations.

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?

Three dense paragraphs, front-loaded with purpose and triggers. Some redundancy with the schema's host enum description, but the approval-flow guidance earns its place. Not overlong given the behavioral nuance it carries.

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?

Covers trigger conditions, host constraints, approval flow, and the 'don't re-ask' rule. Lacks an explicit description of what a successful call returns, but there is no output schema and the key operational facts are present.

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. The description adds no parameter-specific meaning beyond the schema; the per-repo host details are largely redundant with the host enum description. It does not elaborate on companyId, session_id, first_instruction.

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?

Description opens with a specific verb+resource: 'Request a NEW local coding session from voice/chat (tab spawn).' It distinguishes from the attention family by emphasizing 'NEW', and gives concrete trigger phrases. This clearly differentiates it from request_attention_focus/transfer/close.

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?

Gives explicit trigger phrases ('start a Grok/Claude on …', 'new build for …', 'open a session for …') and prescriptive call timing ('Call it on the first clear ask'). It does not explicitly name alternatives for when the user wants to focus/transfer/close, so it misses the 'when-not/alternatives' part of a 5.

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