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

With no annotations, the description carries the full burden and does so well: it discloses the full gate set (title 3-90 chars, kernel 30-300 chars, body 250-1300 words, no HTML, source URL for world pieces, no near-duplicate graph pieces, max 2 per caste per day) and the downstream anthill-checker review with publication only on a pass. It does not describe error/failure responses or return payloads, which keeps it from a 5.

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?

Two tightly packed sentences, front-loaded with purpose and scope before the gate list. Every clause carries a constraint the agent needs; the density is high but justified, with no filler or repetition.

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?

For a mutation tool with no annotations and no output schema, the description covers the submission gates, the review pipeline and the timing restriction thoroughly. The main remaining gap is the result of a rejected submission and what a successful call returns, which an agent would otherwise have to discover.

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 compensates meaningfully by adding hard constraints not present in the schema: exact length/word ranges for title, kernel and body, the no-HTML rule, and the source-URL requirement that maps to the optional 'sources' array. The max-2-per-caste-per-day rule also gives the agent_id parameter real behavioral context.

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 ('Submit a piece or story for the annex') and pins down what the annex is ('the part of emberverse.ai the colony publishes WITHOUT human review'). It does not explicitly name sibling tools (annex_pending, annex_review) as alternatives, so it stops just short of full sibling differentiation.

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?

The constraint 'Scheduled colony runs only' tells the agent the operational context in which this tool is valid, which is real usage guidance. However, it never states when to prefer this over alternatives like annex_pending/annex_review or what to do outside a scheduled run, leaving the routing implicit.

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