List History

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description mainly adds scoping rules. It does add genuine behavioral context — RFC3339 dates, half-open window, pagination requiring identical filters, and a list of rejected parameters — but says nothing about the pagination token's lifetime or result ordering.

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 front-loaded: the core operation, the domain provenance, and the pagination rule come first. Sentences are telegraphic yet each carries distinct information; some reads ('visitor, device and ip have a card, not a list') are cryptic out of context but still earn their place.

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 35-parameter tool with near-zero schema descriptions, the definition leaves meaningful gaps: the boolean flag set, the meaning of snapshot, the limit cap, and the from/to pairing rules are unaddressed. An output schema exists, so return values needn't be explained, which keeps it from being worse.

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?

With only 3% schema description coverage across 35 parameters, the description has to carry nearly the full burden. It names several filters (risk_bands, hre_min_accounts 3-99, hre_min_devices 4-99, ids as one user id on the user list, risk_signals, source, campaign) but lumps roughly two dozen booleans into 'boolean flags', and never explains from/to, limit, snapshot, page_token or response_format semantics.

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 ('List') and resource ('identifications or users in one domain'), which is clearly distinct from the card-style sibling shieldlabs_get_identification. It also disambiguates the resource enum by noting that visitor, device and ip have a card, not a list. It does not, however, contrast with shieldlabs_get_history, leaving that boundary implicit.

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 concrete operational guidance: domain must be the public UUID from shieldlabs_list_domains, page_token must be repeated with the same resource/window/flat filters, and nested filter, chips, offset, include_total and sort are rejected. That is real when/how guidance, though it never explicitly says when to prefer this over shieldlabs_get_history or the card tools.

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