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

Annotations only carry readOnlyHint=false and destructiveHint=false; the description adds genuinely non-derivable behavior: reasons are persisted and read back, won/closed/excluded are terminal, and nothing is deleted. It is consistent with the annotations (nothing destroyed) rather than contradicting them. Minor loss for the cryptic '(CRM-7)'/'(CRM-6)' citations that carry no meaning without external docs.

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 core rule is front-loaded and the 'Effects:' line is efficient, but the middle sentences are convoluted ('then reopen deliberately is not offered: add it again the day it genuinely earns a new place') and reference internal ticket codes that cost tokens without informing the agent.

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?

With no output schema, the description is responsible for outcome expectations, and 'Effects: account.status moved, reason kept' plus the terminal-state guarantees cover that adequately. What an agent would still want - the returned payload or whether the previous status is recoverable - is only partly implied by 'nothing quietly comes back'.

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%, including the enum and the 'Required for on_hold, closed and excluded' note on reason, so the schema already does the work. The description restates the reason requirement without adding format, length, or validation detail beyond it - baseline 3.

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?

'Move an account along the pursuit lifecycle' states a specific verb (move) and resource (account status), and the lifecycle framing makes the transition semantics clear. It never contrasts itself with crm_update_account or crm_promote_to_customer, 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?

It gives real conditions - reason required for on_hold/closed/excluded, terminal statuses, and that re-pursuing a closed account goes through 'a fresh why_them via update' - which implies the alternative path. But no sibling tool is named or explicitly routed to, so an agent must infer which account-mutation tool to use for non-status changes.

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