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

Annotations only say this is a non-read, non-destructive, non-idempotent write. The description adds substantive behavior the annotations cannot convey: metadata edits land in a workspace overlay rather than the global row, contact edits touch global rows only after membership proof, and linking is provenance-bounded to private leads. It does not cover partial-failure or per-lead error behavior, which keeps it out of the top band.

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?

Three dense sentences plus a batch limit, front-loaded with the core verb and scoped by patch type; every clause carries operational information. The heavy domain jargon ("provenance-bounded", "workspace overlays") is terse but not padded.

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?

An output schema exists so return-value explanation is unnecessary, and the description plus annotations together cover mutation semantics, per-patch-type constraints, and the 50-lead cap. Missing only edge-case behavior such as what occurs when membership proof fails or when a leadId resolves to neither store.

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 only 50%, and the description does add the overlay-vs-global-row semantics for the metadata parameter that the schema never states. However, leadId, leadSource, and workspaceId receive no treatment in the description, and the contact/profileLink constraints it repeats are already spelled out in the schema.

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+resource ("Apply bounded lead edits") and enumerates the three edit classes (metadata patches, contact patches, profile link/unlink), which separates it from read/enrich/import siblings like get_leads or enrich_leads. It stops short of naming an alternative, but the operation is unambiguous.

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?

Usage is implied rather than stated: the text tells the agent that contact patches apply to global-row leads and profile link/unlink applies to private leads, which functions as implicit eligibility guidance. There is no explicit when-not and no named sibling to prefer for adjacent tasks such as enrichment or list management.

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