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

No annotations are provided, so the description carries the full behavioral burden for a write operation and does not shoulder it. It never explains the semantics of the 'confirm' flag (default false), whether duplicate detection occurs, what permissions are needed, or what happens to optional fields left blank. Two enum value lists are supplied, but those are parameter-level detail, not behavioral disclosure.

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?

Two short sentences, purpose front-loaded before the value lists, with no filler or repetition. The terse colon-separated enum format is efficient, though it reads more like schema documentation pasted inline than prose structured for an agent.

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?

The presence of an output schema means return values need not be described, and the enum lists are a real contribution. But for an eight-parameter mutation tool with zero annotation coverage, the absence of any guidance on the 'confirm' gate, required-versus-optional handling, or firm_id scoping leaves the definition materially incomplete.

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 0% and no parameter carries an enum constraint, so the enumerated values for client_type (INDIVIDUAL, FAMILY, ENTITY) and pipeline_stage (LEAD, PROSPECT, NEGOTIATION, ONBOARDING) are genuinely additive information the agent cannot get elsewhere. However, six other parameters — including the required display_name and the unexplained 'confirm' and 'firm_id' — receive no semantic treatment, so the compensation is only partial.

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 opens with a specific verb+resource ('Create a new EAM client/prospect'), which is unambiguous and clearly distinct from read siblings like get_eam_clients and mutation siblings like update_eam_client. It stops short of explicitly naming the sibling it is not, so it is clear but not sibling-differentiating.

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?

There is no when-to-use guidance and no exclusions. Given siblings such as convert_prospect and update_eam_client exist, the agent gets no help deciding whether to create a new prospect record versus converting an existing one, or when creating a client should be preferred over updating one.

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