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

Annotations already cover safety (idempotent, non-destructive, closed-world), so the description correctly spends its words elsewhere: it discloses PATCH-style semantics ("Only the paths listed are written") and a hard field exclusion with a pointer to the trace-recording alternative. It stops short of explaining what happens in a partial-write conflict or how approval/proposal state interacts with direct calls.

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 verb plus scope, then the field list, then constraints and workflow in descending priority. The parenthetical field enumeration is long but earns its place given the undocumented 0% schema coverage; nothing is redundant.

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?

Output schema exists, so return values need not be described, and the description covers purpose, writable surface, exclusions, and approval workflow for a complex nested-object tool. The remaining gap is the precise contract between updatePaths and the relationship payload, which an agent must infer.

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%, so the description must carry the load — and it does, listing the writable field families that map to the nested relationship object and implying the updatePaths mechanism via "Only the paths listed are written." It does not clarify the exact string format expected in updatePaths or whether paths are required to match the fields supplied, leaving some ambiguity for a 0%-coverage schema.

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 ("Edits identity and research fields on a relationship") and enumerates the concrete field set (name, firm, title, email, role tags, signal, tier, fit score, citations, connector, terms, notes). It also explicitly differentiates from the sibling fundraising_set_relationship_stage by naming it and stating stage is out of scope.

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 both an exclusion with a named alternative ("The stage cannot be changed here — use fundraising_set_relationship_stage") and a positive workflow rule ("Prefer proposing the edit; call directly only after approval"). An agent knows exactly when to use this tool, when to use another, and what prerequisite gate applies.

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