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

Annotations only supply destructiveHint=true; the description adds the write semantics, the dedup warning, and the underlying endpoint (POST /api/v1/constituents). It does not say what the API returns on success or how it behaves if a duplicate is submitted anyway, but the mutation risk and pre-check are well covered.

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?

Three tight sentences, front-loaded with the WRITE marker and the resource, then constraints, then the dedup pointer. Nothing is padding and the ordering matches how an agent should read it.

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 25-parameter write tool with no output schema and only a destructiveHint annotation, the description covers purpose, required fields, dedup and endpoint. It omits what is returned by a successful create and whether a duplicate is rejected or silently merged, which an agent would benefit from knowing.

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?

With 64% schema coverage and 25 params, the schema does most of the work. The description usefully groups the nested collections (emails, phones, addresses, groups) and ties 'person or organization' to is_org, but it also claims email_addresses is required, which contradicts the schema's required list of only first_name and last_name, making the added meaning partly unreliable.

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?

Opens with a WRITE label and a specific verb+resource ('add a new constituent (person or organization) to the account'), then enumerates the optional sub-resources. That is enough to separate it from lgl_create_gift, lgl_create_note and lgl_update_constituent 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?

Explicitly routes the agent to the alternative: 'Search first (lgl_search_constituents) to avoid creating a duplicate.' It names the sibling and the condition that selects it, which is exactly the when-to-use guidance an agent needs before performing a write.

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