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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior beyond that: the verdict is deterministic and identical for every caller, it never predicts a return or recommends an action, name is null rather than an echoed ticker for a reason, and rows missing an EDGAR date fall back and are flagged filed_at_known: false. These are exactly the non-structural traits an agent cannot get from 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?

Long but front-loaded, opening with the feed's identity and materiality criteria before the verdict semantics, null handling, and access terms. Most sentences carry distinct information, though the verdict explanation and the name-null rationale are somewhat over-elaborated for the space they occupy.

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?

There is no output schema, so the description must describe the returned rows — and it does: verdict line per row, legal name vs ticker with null semantics, and the filed_at_known flag fallback. Together with the cost/auth terms, an agent has enough to call correctly and interpret responses without further probing.

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 67%: slugs and filed_since are documented in the schema, but limit has none. The description explains the date-provenance fallback that underpins filed_since but adds no syntax, format, or range detail for any of the three parameters, so it does not meaningfully exceed the schema baseline.

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 resource (material 13F guru moves) with an explicit materiality definition (new position, full exit, 25% share-count move, or $100M+ position) and ordering rule (newest filing first). This distinguishes it from siblings like guru_portfolio, smart_money_changes, and filings without opening their schemas.

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?

The description gives operational context an agent needs before calling: the endpoint, 0.005 credits per call, and that it works unauthenticated up to 25 calls/day per address. It does not, however, name an alternative sibling or state when-not to use this feed versus guru_portfolio or smart_money_changes, so routing guidance is inferred rather than explicit.

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