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

Annotations only state readOnly=false and destructive=false, so the description adds the meaningful behavioral details: it persists rows, returns a created count, canonicalizes the person handle, and attaches company findings to the person. It does not disclose duplicate/overwrite behavior or auth requirements, but it adds substantial context beyond the annotations.

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?

The definition is front-loaded with the core purpose, then gives tight usage rules in three short paragraphs. Every sentence carries operational guidance; the repeated schema details (person handle, company_domain) reinforce rather than pad.

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 mutation tool with minimal annotations and no output schema, the description covers trigger, batching, content type, person reference, company attachment, and return value. It is just short of a 5 because it does not specify duplicate or upsert behavior if called more than once for the same recipient.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics: pass the lead as a handle already held rather than hand-typing a canonical id, and company findings still attach to a person with company_domain recording the company. It also defines the required content shape as synthesized insight, not raw scraped text.

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?

The description opens with a specific verb and resource: 'Persist synthesized personalization research for leads on an agent,' and clarifies the end result ('what Sliq found'). It separates itself from sibling save/search/record tools by stressing that each finding is synthesized insight, not raw scraped text or article abstracts.

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?

It gives an explicit trigger ('Call this after you synthesize a why-I'm-reaching-out angle'), per-recipient batching guidance, and an explicit content exclusion (not raw scraped content). It does not name the read-side sibling (query_prospect_research) or say when not to call, but the invocation context is otherwise clear among the large sibling set.

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