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

Only destructiveHint=true is provided, so the description usefully labels the operation as a WRITE and gives the underlying endpoint (POST /api/v1/constituents). However it says nothing about permissions/auth, whether a duplicate is rejected or silently created, or what the call returns after the write — the gaps an agent most needs when annotations alone only say 'destructive'.

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 short, front-loaded sentences: write nature first, optional payloads second, duplicate-avoidance and endpoint last. Every sentence earns its place except the inaccurate required-fields claim, which occupies space while misleading.

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 mutation tool with no output schema, the definition covers purpose, optional sub-resources and duplicate avoidance, but leaves out the response shape (e.g. whether the new constituent id is returned for follow-up calls), permission requirements, and duplicate-handling behavior. Adequate but with clear gaps for a tool of this complexity.

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 coverage is 64%, so the description does add value by summarizing that email addresses, phones, addresses and group memberships are optional attachments. But it also asserts that 'LGL's schema marks first_name, last_name and email_addresses as required', and the schema requires only first_name and last_name — a misleading statement that could push the agent into supplying email_addresses unnecessarily. That inaccuracy keeps this below a 4.

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 specific verb+resource ('WRITE: add a new constituent (person or organization) to the account') and enumerates the sub-resources it can carry. It is clearly distinguishable from lgl_update_constituent, lgl_get_constituent and lgl_search_constituents 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 names the alternative (lgl_search_constituents) and the condition that selects it ('Search first ... to avoid creating a duplicate'), which is the primary risk in a create tool. Nothing about when to reach for search versus create is left to inference.

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