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

With no annotations, the description carries the full burden, and it does disclose the most important trait: the call is asynchronous and returns only a proposal id, with the verdict deferred to cycle publication. It says nothing about whether a proposal can be edited or withdrawn, whether submissions are rate-limited, or what permissions the lab requires, which are significant gaps for an unannotated write-style tool.

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 sentences, front-loaded with the verb and resource, then the kind taxonomy, ending with the return contract. The long parenthetical kind list is dense but each gloss disambiguates a distinct enum value, so little could be cut without losing routing information.

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 an 11-parameter, kind-polymorphic tool with no output schema, the description supplies the return shape (proposal id), the async verdict model, and the kind-to-parameter mapping an agent needs to fill the schema correctly. The residual gaps are secondary fields like label and base_thinking, whose schema notes are adequate on their own.

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 82%, so the baseline is 3, but the description genuinely adds mapping semantics: it ties each kind to the parameter it consumes (line/block/example use text, skill uses name plus text, stack uses two to four lines in order, setting uses thinking and effort, route uses model). Only label and base_thinking are left entirely to 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?

The description states a concrete verb and resource ("Propose a part of an AI agent") and then enumerates all eight part kinds with a gloss for each, so an agent knows exactly what can be submitted. It does not explicitly distinguish itself from the similarly-named siblings opsin_market_propose and opsin_perp_propose, leaving the domain split to inference from the names.

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 rather than stated: "Returns the proposal id; the verdict arrives when its cycle publishes" hints that opsin_cycle and opsin_verdict are the follow-up tools, but neither is named as an alternative or next step. Nothing tells the agent when to prefer opsin_propose over opsin_ask, opsin_market_propose, or opsin_perp_propose, and no prerequisites or exclusions are given.

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