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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: the data is 'observed' and 'dated', amounts are 'where disclosed (with basis)', and results include source quotes. It also warns that this is evidence-based rather than exhaustive. This context helps an agent calibrate reliability of results, which is valuable on top of the annotation safety flags.

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?

Three sentences, each earning its place: the first defines the payload, the second lists filters, the third states the value proposition. The structure front-loads the core meaning. It is slightly list-heavy but not bloated; each field named is substantive. It could be tightened by trimming redundant filter names, but overall it is appropriately concise.

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?

For a search/read tool with 8 optional parameters and no output schema, the description covers what an agent needs: it names the return fields (target, sector, asset class, structure, control, lead, amounts, board seats, exits, source quote), the filters, and the caveat on disclosed amounts. The schema fills in parameter details (enum options, id formats, include_candidates behavior), so the combination is sufficient to invoke correctly. It does not mention pagination or default limit, but those are minor for this tool type.

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 63%, so the schema already documents several parameters (since, state, office_dfx_id, investment_kind enum values, include_candidates behavior). The description reinforces the mapping by listing 'sector, asset class, state, kind or since-date' as filter options, which helps connect natural-language filter concepts to parameters. However, it adds little beyond the schema: 'limit' is unexplained (though self-evident) and no new semantics are introduced for the more opaque parameters like asset_class or sector.

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?

The description opens with a specific verb and resource: 'Dated investments family offices have been observed making' and then enumerates the data dimensions (target, sector, asset class, structure, control, lead/participant, amounts, board seats, exits, source quote). This clearly distinguishes it from siblings like search_family_offices (which would return office records) and search_vc_investments (venture-specific). The closing phrase 'The evidence behind "this office backs X"' crystallizes the tool's purpose.

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?

Usage is implied rather than explicit: the description tells you what filters exist ('Filter by office, sector, asset class, state, kind or since-date') and the use case ('evidence behind this office backs X'), but it never states when to choose this tool over alternatives like search_vc_investments or search_allocator_commitments, nor does it mention exclusions or prerequisites. That is adequate but leaves the agent to infer the decision boundary from resource names.

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