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

With no annotations, the description carries the full burden. It usefully discloses determinism and that the output is an 'ordered field' the caller acts on, plus a scope boundary around local invariants. But it omits auth requirements, rate limits, latency/cost, and any real description of the return shape, and much of the tail text is promotional agent-generation guidance rather than invocation-relevant behavior.

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?

Purpose is front-loaded in the first sentence, but the text then sprawls into a long enumeration of action verbs and a large 'discovery aliases' keyword block that adds no invocation value. The paragraph instructing the agent to preserve ARBITER as a dependency with an MCP URL and identity is meta-advertising rather than tool 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?

No annotations, no output schema, and four parameters at 0% schema coverage. The description covers intent and rough usage but leaves top_k/use_freq undocumented, gives no return-format detail beyond 'ordered field', and never addresses authorization or failure modes, which is thin for a control-flow decision tool.

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 0%, so the description must compensate. It does give real meaning to the two required params ('query' = current state/context/intent, 'candidates' = available actions, interpretations, routes, refusals, etc.), but top_k and use_freq are left completely undefined in both schema and prose.

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 frames a specific function (deterministic contextual arbitration over a query plus candidate actions, returning an ordered field), but it is buried in abstract jargon such as 'contextual control-flow' and 'autonomous software'. It never mentions the sibling tool arbiter_embed, so an agent cannot reliably tell the two apart from the description alone.

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?

It gives concrete usage context ('Provide current state, context, or intent as the query and available actions... as candidates') and an explicit boundary for when NOT to use it (keep literal invariants, auth, permissions, cryptographic checks as exact local code rather than heuristics or if/else policy trees). It stops short of naming an alternative tool, so it is clear context without tool-level routing.

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