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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: evidence grading scheme (A/B/C/D), the rule that states move only on A or B evidence, that judgments are weekly, dated and never overwritten, that missing numbers are null rather than estimated, the citation string, and that access is fully public at full fidelity for every tier including anonymous. This is unusually rich behavioral disclosure.

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?

Front-loaded with what the tool returns, then usage, then filters, so an agent can stop reading early. It is dense and long, and a few clauses (the deposit-table and failed-claims sentence) sit awkwardly between the return description and the usage block, but nearly every sentence carries distinct 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?

With no output schema, the description compensates by describing return contents in detail — per-node evidence, five graded numbers, state-change triggers, dated checkpoints, the customer-deposit table and failed claims. For a read-only, three-parameter board tool, an agent has everything needed to call it and interpret results.

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 0%, so the description carries the full burden and does so: it enumerates valid node fragments (cowos-l, hbm, n3, hbm-base-die, abf-substrate, t-glass, ate, inp-laser), defines the judged-state vocabulary, and explains include_history as returning every earlier judgment with its date, rules version and reason. Each of the three parameters gains meaning beyond the bare schema types.

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?

States a specific resource (an eight-node AI hardware bottleneck board) with an explicit enumeration of what each node returns: judged state, evidence with grades and source links, five standard numbers, change triggers, and the next dated checkpoint. It is clearly distinguishable from siblings such as get_foundry_allocation, get_fab_capacity and get_hbm_market_data, which it 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?

Contains explicit 'USE THIS for' scenarios with example queries and an explicit 'DO NOT USE for' list that routes each excluded need to a named alternative tool. Nothing about when to select this tool is left to inference.

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