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

Goes well beyond the annotations: only empty fields are filled, user-written data is never replaced, results say which fields were filled, cached data fills immediately while the remainder completes asynchronously, and there is a daily limit. The 'nothing the user wrote is replaced, so it needs no approval' line sits in mild tension with destructiveHint=true, though it does not directly deny that the tool mutates the graph (readOnlyHint=false is consistent).

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 purpose followed by per-type behavior, batching, and the rate-limit caveat; nearly every sentence carries operational information. It runs a bit long and could split the batch semantics into a tighter clause, but there is no filler.

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 no output schema, it covers what changes, what is preserved, what is returned, sync vs async completion, and a usage guardrail. An agent has everything it needs to call it correctly and to set user expectations.

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 100%, so the baseline is 3; the description still adds real meaning by explaining that 'domain' applies only to a company that has none yet, and that 'object_ids' is the batch alternative to 'object_id' with a 200 cap and background-fill behavior.

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 (enrich/fill empty fields) applied to a specific resource (company, contact, or web link in the user's graph) and anchors it to a known UI action ('the same as the Enrich button'). It also explains the per-type lookup key (website / LinkedIn or email / re-read page), which separates it from siblings like set_graph_object_fields and create_graph_object.

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?

Explicitly says when to use it ('when the user asks to enrich, fill in or flesh out a specific record'), how to handle multiple records (up to 200 ids, background completion), and when NOT to over-apply ('do not run it across the whole graph unasked'). The single-vs-batch routing is spelled out rather than inferred.

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