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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real behavioral context the annotations cannot: every figure carries a source marker [S#], output is a normalized/curated rendering rather than raw disclosure, and check provides validation. It stops short of describing truncation behavior or failure modes in prose.

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 resource and the value proposition, and every clause earns its place, including the long section enumeration which is functionally necessary. The single run-on paragraph with em-dashes makes it denser than ideal, but nothing is wasteful.

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 carries the burden of describing returns and does so: normalized tables, company narrative, change drivers, per-number citations, and a size cap. Remaining gaps are minor – the semantics of the check section and what happens with an invalid section name are not explained.

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 60% and the biggest gap is sections, which is a free-string array with no enum; the description compensates by enumerating the accepted section values (drivers, segment, sga, backlog, texts, check, etc.), which is substantial meaning beyond the schema. It also explains list=true, while stock, period and max_chars are already fully documented 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?

States a specific verb and resource: reading normalized periodic disclosure reports (annual/half/quarterly) rendered in a standard template, including tables, company narrative and change drivers. An agent can tell this is a structured report reader rather than a raw filing search, though it never names the sibling it should be preferred over (search_filings).

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?

Gives useful in-tool routing: use sections to fetch only the parts needed, and list=true to get the report list instead of content. But it offers no guidance on when to choose this over siblings such as search_filings, financials or earnings, and no prerequisites are stated.

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