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

Goes well beyond annotations (readOnly=false, openWorld=true) by disclosing channel-specific behavior, template usage, recipient defaults, the fact that it reaches external people, the default per-call confirmation (which can be disabled), and the API-key requirement. This is exactly the extra context annotations don't carry.

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?

Purpose is front-loaded in the first sentence and every sentence carries information about channels, defaults, or safety. It is slightly padded with app-navigation detail ('Sends the estimate from the Send button of the app') and could be tightened, but nothing is wasted.

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 4-param write tool with no output schema, the description covers channel, recipient defaults, template selection, confirmation behavior, and auth needs. Return-value details are not needed since no output schema exists, but it could clarify the result/state change on the estimate.

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 parameters are already documented. The description adds only marginal meaning (e.g. the `to` may be a primary contact, another saved contact, or a given number) which largely restates schema defaults; baseline 3 is appropriate.

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 (send/email or text), resource (estimate), and outcome (link to view and accept online). An agent can distinguish this from create_estimate, get_estimate, or list_estimates without opening any 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?

Gives clear context: it sends an existing estimate from the Send button, and notes the customer can accept or request a change. However, it never names a sibling or an explicit when-not-to-use condition, so the routing to alternatives remains implicit.

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