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

The annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered and the description doesn't need to restate it. The description does add one genuinely useful semantic hint – that same-period source mentions should not be treated as new earnings events – which is context not present in structured fields. However, it says nothing about how much surrounding context "neighbours" returns or how the four identifier inputs combine to locate the passage, which matters for a lookup whose failure mode is an empty or wrong passage.

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?

It is short and front-loads the purpose in the first sentence, with no filler or repetition. But brevity here shades into under-specification: the caveat sentence is cryptic in isolation and the space saved is not redeployed toward the addressing parameters that actually need explanation.

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?

An output schema exists, so return values needn't be described, and annotations cover safety. What remains missing is essential for invocation: how cik/run/document/block are sourced and combined, and what "neighbours" bounds. For a four-required-parameter lookup with zero schema coverage, the definition is not complete enough for a reliable first call.

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 0% and all four parameters (cik, run, document, block) are required, so the description carries the full burden of explaining them – and it largely fails. Only cik is obliquely referenced ("for this CIK"); run, document and block, which form an unexplained composite addressing scheme, are never mentioned. An agent has no way to learn from this text what a valid run/document/block value looks like or where to obtain them.

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?

"Read a current earnings citation and neighbours for this CIK" gives a verb (read) and a resource (earnings citation/passage), so the general intent is graspable. But key terms are opaque: what a "citation" contains and what "neighbours" means (adjacent blocks? context window?) are never defined. It also does nothing to distinguish itself from the sibling tools get_earnings and get_passage, which an agent would have to disambiguate on its own.

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?

There is no when-to-use guidance at all: nothing explains when to call this versus get_earnings (the parent record) or get_passage (a generic passage fetch). The second line, "Same-period source mentions are not distinct new earnings," is a data-interpretation caveat, not a routing rule. An agent is left to infer the selection logic from the name alone.

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