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

Annotations already declare read-only/idempotent, and the description layers on substantive behavior the annotations cannot express: XBRL coverage boundaries by company size and date (mid-2009 / mid-2010 / mid-2011), the night-after-filing lag for tags, missing refs for dash (zero) lines and pre-mid-2019 filings, and the larger response size with include_tags.

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 purpose, then workflow, then coverage caveats, then args — the ordering is sensible. The include_tags block is long and paragraph-dense, though nearly every clause carries information an agent would otherwise have to discover by error.

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?

Given a simple 3-parameter read tool with an output schema, the description covers the remaining unknowns: coverage limits, failure mode for early filings, tag latency, and the outbound escalation path for older years. Nothing an agent needs to call it correctly or interpret an empty result is missing.

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 must carry the load, and it does: cik gets a concrete example, accession_number is scoped to 10-K/10-Q, and include_tags is explained in depth (concept + axis members + unit, full-unit values, printed text, ref for check_citations, highlight_url) along with when it is unavailable. This is meaning well beyond the bare boolean default in the schema.

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?

Specific verb plus resource ("Extract structured financial statements from a 10-K or 10-Q filing") followed by an explicit enumeration of what comes back (balance sheet, income statement, cash flow, equity, comprehensive income). It is clearly distinguished from siblings get_filing_item (raw Item 8 text) and get_financial_history.

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?

States the prerequisite workflow explicitly: find an accession number with get_filings, then pass it here. It also names the alternative for out-of-coverage filings ("read a 10-K's Item 8 with get_filing_item") and advises reducing statements/filings when include_tags is set.

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