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

Adds substantial context beyond annotations: async/queued behavior, ~1-3 minute background write time, credit consumption with a specific failure message when credits are exhausted, and an explicit 'no auto-publish path' guarantee. Annotations only cover readOnly/idempotent hints; the description carries the operational reality.

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 one-line purpose, then async/cost details, then the polling workflow, then the no-publish guarantee, then args. Every paragraph earns its place with zero filler.

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?

Given 6 params, no output schema, and an async tool, the description covers the lifecycle (queue → background → poll → read fields), cost model, error condition, and publish boundary. Nothing an agent needs in order to call and follow up 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?

Schema description coverage is only 17%, so the description must compensate. It does for most: primary_prompt with an example and 3-500 char constraint, secondary_prompts as 'extra angles', word_target 300-6000 with default, template_id purpose. brand_id is only labeled 'required' with no extra semantics, and user_intent (an analytics hint) is never mentioned in the description despite being 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 ('Generate a brand article') and immediately distinguishes itself from get_articles (reads) and generate_report (sibling asset type). An agent knows this is the write/generation entry point for articles.

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 workflow: call this, then poll get_articles(brand_id, view='detail', article_id=<id>) until status is 'draft' or 'error', then read content and llm_score. Names the exact follow-up tool and terminal states, so no inference is needed.

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