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

With no annotations, the description carries the full disclosure burden, and it does substantial work: it identifies data provenance ('raw clearinghouse state', 'latest desk mark', 'v7.5 trade veto') and marks the payload as a point-in-time snapshot of live externals, which tells the agent values drift between calls. It omits explicit read-only/no-side-effect confirmation, caching or rate-limit behavior, and failure modes when a venue is unreachable, so it is not complete.

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?

The lead clause is well front-loaded and tells the agent immediately what this is. But the body is one marathon sentence enumerating seven data domains, and the text is visibly truncated mid-word ('currently positio'), which leaves the reader unsure whether a clause was lost. The enumeration earns its place; the packing and the truncation do not.

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?

There is no output schema, so the description must describe return values — and it does, domain by domain, which is exactly the right compensation. The main shortfall is the truncated final clause and the absence of any note on payload size or partial-failure behavior for an aggregate that stitches together multiple external venues.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly implies the entire desk scope is returned unconditionally, with no filtering options to explain.

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 specific resource — a live trading desk state snapshot — and enumerates exactly what it returns: Hyperliquid equity and perp positions, Polymarket cash and combined desk value, armed fixtures, stake ladder, sentiment veto vector, and edge tape rows. That is far more specific than a sibling like akari_hl_market or akari_inplay_edge, which appear to cover single slices. It does not explicitly name which sibling to use for the narrower slices, so it stops short of a 5.

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?

'Use for desk mirroring, copy-trading context, or checking what a live trading agent is currently positio[ned]' gives concrete positive use cases, which is more than most definitions. However there are no exclusions or routing rules — nothing says when to prefer akari_inplay_edge or akari_hl_market for a single data slice instead of pulling this whole aggregate. Usage is implied by the content list rather than prescribed.

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