get_pulse

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

With no annotations to lean on, the description carries the full burden and delivers extraordinary disclosure: the feed is 'NOT A BALANCED MIX', it is 'ordered by ingest recency', and it reveals a measurement that the newest 100 rows were '100% kind: ownership, all from one registry' (2026-08-11). It even corrects prior misinformation ('NOT GLEIF as earlier versions of this description claimed') — the kind of bias disclosure that would be invisible to an agent without this text.

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?

The description front-loads the core definition, then usage, then warnings — good structure with strong leading content. However, the measurement statistics (100/100, dates, percentages) appear twice: once in the main prose and again inside the `kind` enum descriptions, creating slight redundancy. Every sentence otherwise earns its place; the uppercase emphasis is effective but the near-duplicate measurement reports could be consolidated.

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?

Given there is no output schema and no annotations, the description fully compensates: it covers what is returned (events with a source registry), ordering semantics, parameter behavior, per-kind meaning, and dangerous default-bias caveats. For a monitoring/feed tool of moderate complexity, there is nothing essential an agent needs to know that the description omits — it even notes when defaults 'move as loaders run,' setting correct expectations about non-determinism.

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?

Although schema coverage is 100%, the description goes far beyond, defining each enum value with measured composition — e.g., 'watchlist = OpenSanctions non-sanctions listings — politically-exposed persons, criminal/wanted entries and procurement debarments, not PEPs alone' — and clarifies the registry source (borme/companies_house/opensanctions). `since` is meaningfully framed as a sync cursor for polling rather than a plain date filter. This is exactly the value the schema's one-line hints forfeit.

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 crisp noun phrase identifying the exact resource and behavior: 'The WhiteIntel Pulse activity feed: recent corpus events... newest first, each with a source registry.' It enumerates the four event kinds, states the ordering, and notes provenance — a specific verb+resource that is impossible to confuse with the sibling search/lookup/graph tools despite no sibling being named.

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?

Provides an explicit when-to-use: 'Use this to answer "what changed recently" or to monitor the corpus.' It also supplies when-not-to-infer guidance ('do not infer "nothing else happened" from the default page') and instructs the agent to pass `kind` when it wants a particular stream. This directly helps the agent choose between this and the search/entity siblings, even without naming them.

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