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

Beyond the destructive/openWorld annotations, it discloses workspace scoping, that unknown/forbidden ids surface in 'skipped' or 'refused' rather than failing the call, non-atomic behavior, and the full propose→confirm flow with action_id and plan_token. This is exactly the behavioral context an agent cannot infer from structured fields.

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 core action, then progressively narrower details (refusal rules, atomicity, confirmation). Dense but nearly every clause carries operational meaning; the caps-lock emphasis on MANY and CONFIRMATION is functional, though the single paragraph could be split for scanability.

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?

A destructive, 5-parameter bulk mutation with no output schema, yet the description covers inputs, failure semantics, refusal codes, and the two-step confirmation handshake including the exact status string an agent should expect. Nothing needed to call it correctly is missing.

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 0% schema description coverage, the description carries the load: it explains lead_ids as the batch input, notes status and priority are alternatives ('and/or'), and gives the conditional lostReason requirement tied to the 'unqualified' enum value. lostComment is never mentioned and the 500-id cap is left to the schema, so it stops just short of full coverage.

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 (apply status/priority change), resource (CRM leads), and scope (MANY at once), with a concrete example. It distinguishes itself from the singular update_lead and from crm_bulk_set_stage, which is named as the tool for stage moves.

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?

Explicit routing: status 'unqualified' requires lostReason, and leads in a workspace pipeline are refused with a 'use_stage' signal pointing to crm_bulk_set_stage. The batch example (marking new Facebook leads in_progress) anchors when to reach for this over a per-lead update.

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