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

Annotations already declare this is a non-read-only, non-destructive, closed-world write. The description adds a safety boundary (not for emergencies or crisis) but never says what actually happens on invocation — whether a lead is recorded, whether the work email is contacted, or what the caller gets back. It also omits the 18+ tap-token precondition that the schema hints at.

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 positive trigger is front-loaded in the first sentence, with exclusions following in short parallel clauses. It is appropriately short for a routing-sensitive tool, though the repeated 'Not for...' fragments are slightly list-like rather than fully composed prose.

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 5-parameter write tool with no output schema, the description covers eligibility and exclusions well but leaves the outcome undefined — no statement of what a 'pilot' start produces or what the agent should tell the user afterward. Annotations carry the safety profile, so the remaining gap is moderate rather than severe.

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 every parameter including tap, company, country, team_size and work_email is already documented. The description only echoes the two required fields (company, work email) without adding format rules such as requiring a corporate rather than personal email domain. Baseline 3 applies.

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 states a specific intent: trying 2hives with a work team or company, gated on a company name and work email. Combined with the title 'Start a team pilot', an agent can identify the action. It stops short of naming siblings such as create_team or join_team, so the boundary against those team tools must be inferred.

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 an explicit trigger ('when the user wants to try 2hives with a work team or company and gives, or can give, a company name and work email') and three explicit exclusions: medical/emergency/crisis, general meditation chat, and personal listening. The when-not list is unusually thorough for a routing decision.

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