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

Beyond the annotations (readOnlyHint/openWorldHint/destructiveHint=false), the description discloses non-obvious behavioral facts an agent would otherwise get wrong: bi-monthly batch publication, the cnsfails<YYYYMM>a/b split, the 2-4 week publish lag, and an explicit warning that apparent staleness is SEC cadence rather than a freshness bug. It also defines the derived fail_value field and its reference price.

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?

Well front-loaded: purpose, then row semantics, then signal value, source, coverage, query patterns, then caveats. It is long and the 'Signal value' interpretation (naked short pressure, locate mechanism breakdown) is arguably padding for a retrieval tool, but the structure is clean and each remaining sentence carries usable 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 a 10-parameter, zero-required, no-output-schema tool, the description covers source, publication cadence, coverage universe, row grain, derived fields, and concrete query recipes. An agent has everything needed to select filters, sort correctly, and interpret freshness without a return-value schema.

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 100%, so the baseline is 3, but the description adds real meaning the schema lacks: it defines fail_value = quantity_fails × price and its reference-price source, and gives worked examples for min_value and min_quantity thresholds plus when to prefer cusip over ticker. It stops short of documenting id/since/until/limit/sort_order beyond what the schema already says.

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 names a specific verb+resource ('Returns SEC Fails-to-Deliver (FTD) rows — daily settlement failures by ticker / CUSIP / date') and immediately scopes what one row means (one ticker on one settlement date). It is clearly distinguishable from the many sibling datasets (insider filings, institutional holdings, etc.) because it pins the exact SEC dataset and grain.

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 provides explicit 'Killer query patterns' with concrete parameter combinations for each intent (daily history, largest FTDs this month, squeeze candidates, CUSIP lookup), which is strong when-to-use guidance. It does not, however, name an alternative tool (e.g. unified_search) or state when this tool should be avoided, so it stops short of full routing guidance.

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