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

Annotations already declare readOnly/openWorld/non-destructive/idempotent=false, and the description adds substantial behavioral context beyond them: deterministic, no credit cost, Pro-plan gate with error=plan_required messaging, and the meaning of a BLOCKER. It stops short of describing pagination or rate limits, but the safety and cost profile is well covered.

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 prose is dense and long, but front-loaded with the core purpose and cost/plan facts, and nearly every sentence adds actionable detail (output shape, conditional blocks, prereq, error handling). Given 9 parameters and no output schema, the length is largely justified, though some return-value enumeration borders on redundant with the schema.

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 fully carries the burden: it documents the slop index scale, the five component scores, findings with spans, the SEO head handling, and the conditional shape/voice/fidelity blocks. An agent has enough to call it correctly and interpret the result.

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 100%, so the baseline is 3, but the description adds genuine usage guidance beyond the schema: passing site_domain for same-site link checks, expect_front_matter=true for a publishable draft, and the conditional response blocks that site_id, original, and shape produce. This helps select parameters, though it largely mirrors schema-specified 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 and resource ('review of ANY text or public URL') and immediately scopes what it returns (slop index, component scores, findings) and its constraints (deterministic, no credits, no brief needed). An agent can distinguish it from rewrite_content or score_content_draft because it positions itself as a measurement-only reviewer with a defined output shape.

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 when-to-use is given: 'Run it before you show a draft to the user and after every revision', plus a prerequisite ('read the writing_guardrails prompt before drafting'). It also handles the plan_required error path and clarifies that BLOCKERS are what publish_content_brief refuses, routing the agent downstream.

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