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

Annotations already declare readOnly/openWorld/non-destructive, and the description layers substantial extra context beyond them: unit multiplicity (USD vs USD/shares), YTD-cumulative vs quarterly observations and the frame marker, deprecated concept-name migration, latest_only collapsing to one row per ticker×concept, and an explicit 'pure-publisher' posture (no derived ratios). This is exactly the behavioral detail an agent needs and could not get from the annotations.

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 the core purpose, then organized into scope, cautions, and posture blocks that each carry distinct information. It is long and the 40-concept watchlist is verbose, but nearly every line earns its place; trimming is possible but not warranted enough to drop below a 4.

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 13 parameters, no output schema, and a specialized financial domain, the description supplies the scope (concept watchlist), the record grain, the data-interpretation hazards, and the deliberate non-computation boundary. An agent has everything required to call and interpret this tool correctly.

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 100%, so the per-parameter text already carries the basics. The description still adds meaning on top: it explains latest_only's per-ticker×concept collapse, lists the concept categories behind the category enum, and clarifies the frame/period semantics that govern how results should be interpreted.

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 verb and resource: 'Returns XBRL-tagged financial fundamentals from public-company 10-K and 10-Q filings, sourced from SEC EDGAR's company-facts API,' and clarifies the record grain ('one observation of one concept at one period end'). It never names distinguishing siblings such as get_annual_financial_disclosures or get_bank_financials, so an agent must infer the boundary rather than being told 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?

Provides an explicit trigger list ('Use this when the user asks about: revenue, profit, margins, cash position, debt...') that maps user intents to the tool, which is strong positive guidance. There is no 'when-not-to-use' clause and no named alternative for overlapping needs, so routing vs siblings is left implicit.

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