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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description still adds real value: partial-update semantics, the default-preservation rule for subscribed, the unsubscribes/re-subscribes consequences of that flag, and the consent liability statement ('this server never subscribes anyone on its own'). It does not, however, discuss tag-removal or unsubscribe irreversibility beyond the consent note.

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 WRITE label and the field list, then progressively narrower rules, ending with the PUT path. Dense but nearly every clause carries information. Minor redundancy in restating the mutable fields already implied by the verb.

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 an 11-param, zero-required, no-output-schema mutation tool, this covers the risky surface (subscription, consent, partial update). Gaps remain around identifier selection (email vs lead_hash) and the add_tags/remove_tags ordering interaction, which are only resolved by opening the schema.

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, the description adds meaning beyond the schema by explaining the merge-tag keying for `fields`, the send-only-what-changes contract, and the detailed conditional semantics of `subscribed` (false unsubscribes, true re-subscribes, consent required). It does not clarify the email-vs-new_email-vs-lead_hash identity relationship, which the schema only partly covers.

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 'WRITE: change an existing lead's name, custom fields, email, timezone, IP address, subscription flag or tags' — a specific verb plus resource plus the full mutable field set. The 'WRITE' prefix and 'existing lead' scope cleanly separate it from create_lead, get_lead, and the update_order/update_product siblings.

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?

Gives clear operational context: 'send only what should change' (partial update), 'subscribed is left alone unless you pass it', and the consent precondition for subscribed=true. It also routes to mailbluster_list_fields for merge tags. It never explicitly names a sibling alternative (e.g. create_lead for new leads, get_lead to inspect first), so it stops short of a 5.

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