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

With no annotations provided, the description carries the full behavioral disclosure burden. It does this well by explicitly stating that the tool returns aggregate counts only, never names unreviewed records, and includes caveats about interpreting statuses and the ingest_enabled flag. It stops short of describing the full response shape or exact fields, but for a zero-parameter health tool, it discloses the key behavioral expectations.

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 is compact but information-dense, with no filler or repeated content. It front-loads the core purpose, then adds essential caveats in logical order: what it reports, what it never does, when to use it, and how to interpret flags. Every sentence earns its place and contributes to safe, correct use.

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, the description does a good job of explaining the conceptual contents of the response: source states, review queue depth, published counts, and pointer reachability. It also names the degraded_reasons field and the ingest_enabled flag, giving the agent concrete anchors for interpretation. It could be more complete by enumerating exact response fields, but it provides enough context for correct invocation and basic interpretation.

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?

The tool has zero parameters and the schema is fully described with an empty properties object, so there is no parameter semantics burden on the description. The description instead focuses on the meaning of the output, which is the more relevant semantic content for this tool. Baseline 4 is appropriate for a 0-parameter tool.

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 clearly defines the tool as a health/status monitor for the Palestine evidence pipeline, listing exactly what it reports: source collection status, last success times, review queue depth, published counts, and external pointer reachability. It also distinguishes itself from sibling tools by stating it provides aggregate counts only and never names unreviewed records, making its role distinct from evidence_search or evidence_record.

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 a direct use case: 'Use it to answer "is this archive current?" honestly before citing it.' It also provides interpretive guidance, telling the agent to read degraded_reasons rather than relying on status alone and explaining that ingest_enabled:false means configured off, not broken. This prevents common misuses and clarifies when the tool is appropriate.

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