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

Goes well beyond the annotations: it discloses that no CRM record is changed, nothing is spent, and the change is captured in configuration history with Undo. This usefully reframes the destructiveHint=true annotation as destruction of the prior TAM config (reversible) rather than CRM data, without contradicting it.

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?

Front-loaded with the core action, then layers constraints, prerequisites, and side effects efficiently. It is dense and slightly run-on, but virtually every clause carries information that affects correct invocation or safety.

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-parameter write tool with rich schema coverage and annotations, the description supplies the prerequisite, the parameter relationship rules, and the side-effect/undo profile. It stops short of noting auth/permission requirements, which is the main residual gap.

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?

Adds real meaning over the 100%-covered schema, notably the cross-parameter constraint that account and persona 'may be null but not both', and the role of icp as narrowing criteria on top. Much of the field framing ('filter groups over accounts/contacts') does echo the schema descriptions, keeping this just above the baseline.

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 ('Save the connection's TAM') and immediately fixes the scope with 'replacing what it holds', which separates it from the read-side siblings get_tam/get_tam_outward. An agent can tell this is the write/mutate counterpart 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?

Provides a concrete prerequisite ('Call list_filterable_fields for each object first') that is essential to correct invocation. It does not, however, route the agent away from alternatives or state when this tool should be preferred over get_tam/get_tam_outward, so it stops short of the explicit when/when-not bar.

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