edgar_company_concept

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

Annotations only declare readOnlyHint and openWorldHint; the description carries a heavy load and exceeds it. It discloses the (start,end)-pair period identity rule, the canonicalOnly dedupe that is 'fully disclosed, never a silent drop', 'val is null-never-0', 'NEVER fabricated val:0' on 404, throw-on-shape-drift, and the CIK-not-SAM-UEI caveat. This is model-grade transparency about failure modes and data semantics.

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?

Dense but justified for a 9-parameter tool with no output schema; the return shape is compactly inlined and the honesty notes are organized under a labeled 'HONESTY M1' marker. It front-loads purpose and differentiators before details. Slightly over-stuffed — the error-semantics section could be trimmed — but every sentence earns its place given the complexity.

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?

Remarkably complete for a tool with no output schema: it inlines the full return object shape, enumerates error classes (404 vs 5xx vs non-JSON/shape-drift vs missing unit), documents pagination semantics (limit/offset are client-side over a fully-fetched series; SEC does not paginate), and warns about the CIK↔UEI gap. Nothing an agent needs to call it correctly or interpret results 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 100%, so baseline is 3, but the description genuinely adds meaning: it flags which parameters are CLIENT-SIDE versus path segments (unit, form, fy, limit/offset), explains canonicalOnly's dedupe key (unit,start,end), and links unit semantics to the disclosed-units behavior. The description reinforces and extends the schema rather than merely repeating it — though the schema itself is already unusually rich, so the marginal gain is modest.

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?

Opens with a crisp triple: 'One filer × one XBRL concept × complete reported time-series' — a specific verb-less but precisely scoped resource statement. It then names both sibling tools and the exact axis that differentiates them ('Sits between edgar_company_facts (many concepts, one filer) and edgar_xbrl_frames (one concept, all filers)'). An agent can disambiguate immediately without opening any schema.

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?

Explicitly positions the tool relative to its two nearest siblings and enumerates the input contract (cikOrTicker, concept, optional taxonomy/unit/canonicalOnly/limit/offset). It also states when NOT to expect success — bad CIK/taxonomy/concept yields 404→found:false, unit-not-present yields honest empty — which tells the agent how to interpret outcomes and when to route elsewhere.

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