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

Annotations already declare readOnly=false, destructive=false, idempotent=false, openWorld=false, so the safety profile is covered. The description adds meaningful context beyond that: it is an evidence-recording write that does not verify, consent, enroll or send, and it requires the outreach:write scope. It omits what happens on repeated calls, which matters given idempotentHint=false.

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?

Two compact sentences with the scope statement front-loaded and no filler. The trailing permission sentence is short and functional, though the enumeration of observation types is dense enough that it reads more as a checklist than prose.

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 15-parameter mutation with no output schema and no per-property descriptions, the description covers intent, boundaries and auth but leaves gaps: it does not describe the response, error behavior, or field-level semantics. The schema's 'omitted fields stay unchanged' note helps but is not restated or expanded in the description.

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% across 15 parameters, so the description must carry the burden. It names only broad categories (identity, employer, email, mailbox result/expiry, source policy) and does not explain the actual fields an agent must fill — e.g. how identity_url differs from employer_url, what upstream_source_key or email_provenance_url accept, or how the *_observed_at timestamps relate. Required vs optional (only lead_id is required) is also unaddressed.

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 ('Record') plus a concrete resource ('outreach evidence') and enumerates the kinds of observations captured (identity, employer, published work email, mailbox result/expiry, source-policy). It does not, however, contrast itself with adjacent siblings like update_outreach_lead_status or add_outreach_lead, so sibling differentiation is left implicit.

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?

The description draws useful boundaries ('does not independently verify facts, create consent, enroll or send') which tells the agent what this tool is not for, and notes the required permission 'outreach:write'. But it never states positively when to choose this over the similarly-scoped outreach siblings, so routing guidance is only implied.

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