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

With no annotations, the description carries the full burden and does deliver real behavior: an authentication requirement, an atomic write that records 'current contribution terms', a refusal condition for bare comparator declarations lacking a content-addressed corpus, and a compatibility floor where a missing `problem` falls back to the title. That is substantive, but it omits what is returned, what other failure modes exist, and whether proposals are editable or withdrawable afterward.

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?

A single monolithic run-on paragraph of very long sentences, front-loaded with an unexplained 'AUTH:' token rather than the core action. Nested requirements (comparator classes, prerequisite bounds, contribution-term pinning) are interleaved with field names instead of being separated into scannable guidance.

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 no-annotation write tool with a complex nested payload and no output schema, the description does cover auth, the field set, and several failure conditions. It still leaves gaps on what the call returns and on the full validation surface, and the density undercuts its usefulness in practice.

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?

Nominal schema coverage is 100%, but the actual schema is a single opaque `proposal` object with no field documentation, so the description must supply field meaning — and it does enumerate title, problem, kind, form, english_mapping, rationale, predicted_measurement, colony_thread_url, and optional evidence_contract/slot/corruption_neighbors/form_constraints/examples. However, the nested `evidence_contract` and `claim_carrier` semantics are written in dense internal jargon that an outside agent cannot reliably act on.

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?

The opening 'file a construct proposal' gives a specific verb plus resource, and the reference to 'Same fields as POST /api/v1/proposals' anchors it to a known surface. But the 'AUTH:' prefix is cryptic, and the purpose is then buried under several hundred words of field jargon before an agent can confirm it is the create-proposal tool rather than, say, a voting or suggestion tool.

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?

There is no statement of when to use this versus siblings such as `second`, `suggestion_feedback`, or `vote`, and no prerequisites beyond the bare 'AUTH:' tag. An agent must infer from the name alone that this is the submission step of the workflow.

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