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

Annotations cover safety (not read-only, idempotent, non-destructive), and the description adds genuinely new behavior: partial-update semantics ('only the fields you pass change') and the external consequence that the first save routes the agency for partner approval. It stops short of stating permissions, validation failures, or what the caller sees after submission.

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 account scope, then mutation semantics, then the approval consequence. Every clause carries information; nothing is padding.

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?

With no output schema and a rich annotation set, the description covers the essentials an agent needs: which account type, partial-update behavior, and the approval workflow trigger. It omits only secondary detail such as what happens on subsequent saves after approval.

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 80% and the schema already carries the same hints (including 'Required on the first save' for agency_name and the client-count clarification). The description largely restates field meanings already documented in the schema rather than adding format, range, or validation detail.

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 (save/change) and resource (the caller's agency details) and enumerates the exact fields in scope. It is immediately distinguishable from read-oriented siblings like my_agency or my_shearquery_account.

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?

Scopes the tool to AGENCY accounts and gives an operating procedure ('ask for them in conversation and read them back before saving'). It does not name alternative tools, but no sibling performs this write, so the routing need is minimal.

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