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

Goes well beyond the annotations: discloses the caller-ownership constraint and cross-tenant rejection, states idempotency (re-linking does not duplicate), explains that 'remove': true drops the link while both records survive, and clarifies the confirmation model — this runs immediately and returns an ordinary result rather than a plan_token, unlike destructive/outbound/financial operations. That is exactly the operational context destructiveHint=true alone cannot convey.

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 core action and linkage model, then parameters, then edge cases — a sensible order with no filler. The CONFIRMATION block is longer than strictly needed for selection purposes, though it does prevent a real misuse (expecting a plan_token), so the length is defensible rather than wasteful.

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 5-parameter mutation tool with no output schema, the definition covers the linkage model, ownership preconditions, idempotency, undo, alternative routing, and even the shape of the response. Nothing an agent needs in order to call it correctly or explain the result to a user is missing.

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 0% schema description coverage the description carries the full burden and does so: it names lead_id, object_type with its four enum values, object_id, the optional 'note' label with concrete examples («CEO», «introduced us»), and the boolean 'remove' as an undo of the link. Every one of the five parameters gains meaning the bare JSON schema does not provide.

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 (link a personal record to a CRM lead), enumerates the supported object types (note/task/meeting/contact), and names the visible outcome (appears on the lead timeline and on the person's card in get_person). It also distinguishes itself from create/update_contact_personal 'relations', so an agent can route person↔person cases away without opening another 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?

Explicit when-to-use (attach a personal note/task/meeting/contact to a lead), explicit when-not/alternative (person↔person goes through create/update_contact_personal 'relations'), and an explicit undo path via 'remove': true. The ownership precondition (both records must belong to the caller; cross-user/cross-tenant rejected) further scopes valid usage.

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