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

Beyond the annotations (readOnly=false, destructive=false, openWorld=true), it discloses genuinely useful behavior: a confirmation prompt per call, that the action reaches other people outside the workspace, and that a Cotlet API key with app access is required. It stops short of describing delivery/return behavior, but the safety-relevant context is present.

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 first two sentences say the same thing twice in nearly identical words ('Email or text a contacted customer... as free text or one of your saved templates' followed by 'Emails or texts a customer you already contacted... as free text in body or from one of your saved Email or SMS templates'). The rest is well front-loaded, but the duplication wastes the most prominent space.

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?

There is no output schema and annotations are minimal, so the description carries most of the burden — and it does cover destination rules, content modes, confirmation behavior, and auth needs. It could still say more about what happens on send (e.g., failure/channel constraints), but it is largely sufficient for a 4-parameter mutation tool.

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 the schema already documents all four parameters, making 3 the baseline. The description adds only 'Required: body or template', which is a partial framing that omits the schema's actual required keys (lead_id, channel), so it contributes little and is slightly loose.

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?

It names a specific verb and resource (email/SMS a customer you have already contacted) and adds the key scoping constraint that distinguishes it from siblings like bark_contact_lead, which contacts new leads. An agent can tell what this tool 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?

It states when to use it (an already-contacted customer), gives the two content modes (free-text body vs. saved template), and notes that per-call confirmation is on by default and can be disabled. It does not explicitly name an alternative tool or state when not to use this one.

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