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

Annotations already establish read-only, idempotent, non-destructive behavior, so the bar is low, yet the description adds substantial context beyond them: the named decision rules, the deliberate ignoring of sunk money and time, and the full shape of the returned call (score, rule, reason, next action, next review date, what would flip it, portfolio notes).

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?

Purpose and scope are front-loaded, and the rule sentences earn their place because they define the tool's decision logic. It is dense and slightly run-on, and promising '10 named decision rules' while enumerating only five creates a small structural gap.

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 usefully describes the return payload, so an agent knows what it gets back, and it discloses the sunk-cost stance. It is complete enough for invocation, though it does not say what happens on malformed or partial product input.

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 67%, and the description adds real meaning by tying inputs to outcomes: metrics (target, actual, kill line, must-hit), evidence, stage, review date, last activity, monthly revenue and cost all map to specific rules. It does not explain the defaults (kill_at, weight, direction) that the schema itself documents.

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+scope: makes a push/iterate/park/kill call on 1-12 products from their metrics and evidence. That is clearly distinct from sibling tools such as build_scope_and_sequence, cut_mvp or sequence_build, which deal with shaping and ordering work rather than ending or continuing a product.

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 by the decision-rule content (you run this to judge whether to keep building a product), but the description never says when to reach for this tool versus the sibling planning tools, nor what input conditions make it inappropriate. No explicit alternatives or exclusions are offered.

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