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

With readOnlyHint/openWorldHint/idempotentHint already declaring the safety profile, the description still adds meaningful behavior: the sheet is free, states are derived, 'empty' is data not an error, 'dark' carries the exact blocker, and an unknown/delisted asset yields a typed UNKNOWN_ASSET refusal. It does not describe pagination or return shape, but the output schema covers returns.

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 core purpose is front-loaded, but a large fraction of the description is a corrupted 'available set' list with heavy duplication (X05 five times, X06/X07 etc. repeated) that adds no information and contradicts the 'eleven questions' claim. That bloat does not earn its place and dilutes the useful content.

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 tool with an output schema and covering annotations, the state semantics, agent loop, free access, and refusal behavior are adequately covered. Gaps remain: the wallet parameter is unexplained and the internal inconsistency between 'eleven questions' and the S01–S26/X-series list leaves the agent unsure of the actual scope.

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 only 50%: 'asset' is documented in the schema, but 'wallet' has no description in either the schema or the description. The text says 'for one asset' and mentions needs_wallet inside rows, but never explains what the wallet input does, so the description fails to compensate for the coverage gap.

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 states a specific resource and scope: for one asset, the eleven catalog questions (S01…S11) each with a derived state (live/pending/empty/dark) and an ask block. That is a clear verb-less read resource, but the purpose is muddied by the later claim that the available set spans S01–S26 and X05–X09, which contradicts 'eleven questions' and undermines the scope. No sibling (e.g. tollbridge_open_clocks, tollbridge_call) is named to differentiate it.

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 'AGENT LOOP' gives real conditional guidance: read the sheet, sleep to min(horizon_end) if a row is pending, read the resolution, then ask ONLY rows where ask.allowed == true. However, it never says when to prefer this tool over tollbridge_open_clocks, tollbridge_call, or tollbridge_decision, so usage context is implied rather than routed.

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