Unredactus metadata research

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description does add genuine scope expectations beyond that: it tells the agent what will NOT be returned (names, passages, private identifiers) and that counts are 'source-reported', which sets expectations about fidelity. It stops short of saying what happens when the ID is unknown or refers to a non-public document.

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?

Two tight sentences with the resource and returned fields front-loaded, followed by the negative scope. The disclaimer clause is the least informative part but still carries behavioral meaning rather than filler.

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?

With no output schema, the description must carry return-shape information and it does list the returned categories. What remains missing is behavior for non-public or unknown IDs and whether provenance here duplicates read_snapshot_provenance, leaving an agent uncertain about results in edge cases.

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?

One required parameter with 0% schema description coverage, so the description carries some burden. It does add the important qualifier that the ID must be public, but it never mentions the 'EFTA########' format that the schema's pattern encodes, so an agent reading only the description could pass a malformed ID. Partial compensation for the coverage gap.

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 names a specific verb and resource ('Read one public source document ID') and enumerates what comes back (change counts, classifications, snapshot provenance). It implicitly separates itself from search_document_metadata via 'one ... ID', but it never names the sibling it overlaps with most, read_snapshot_provenance, which also appears in its own return list.

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?

There is no explicit statement of when to use this versus search_document_metadata (lookup by known ID vs discovery) or read_snapshot_provenance (provenance is claimed here too). The only signal is the word 'one', which an agent must infer from. No preconditions, no exclusions.

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

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the data is a point-in-time snapshot (potentially stale) and the tool does not perform verification, warning the agent not to treat the output as authoritative. It does not say where the snapshot comes from or how it is selected.

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?

Two short sentences, front-loaded with the resource and its returned contents, then a single scoping caveat. Dense but no wasted sentences; "evidence limitations" is slightly opaque but earns its place as a returned-field label.

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?

With no output schema, the description usefully enumerates the returned fields, which compensates well. But a zero-parameter tool reading "snapshot" provenance raises an unexplained question: which snapshot is read (global/current only)? That scoping gap plus the absence of output structure leaves an agent guessing about the response shape.

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, so there is nothing the description needs to explain at the parameter level. Baseline of 4 applies; no parameter claims are made or contradicted.

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 (read) and resource (snapshot provenance) and enumerates exactly what is returned: snapshot dates, pinned upstream commit, source hashes, license, counts, evidence limitations. It does not name the sibling tools or differentiate itself from read_document_metadata, so it stops short of a 5.

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 second sentence gives a useful negative boundary ("not a live monitor or independent verification"), which implies when to avoid it. However, it never says when to prefer it over read_document_metadata or search_document_metadata, leaving the positive selection criteria to inference.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds real domain context (no person search, no removed-text passages, preserve automated/triage labels and false-positive states), but 'bounded' is never quantified and the count/offset caps are left to the schema.

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 short sentences with the resource and scope front-loaded and no filler. The trailing 'Preserve automated/triage labels and false-positive states' is terse to the point of being cryptic, but it is short and earns its place as a usage constraint.

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?

With five parameters, 0% schema coverage, two unexplained enums, and no output schema, the description leaves significant gaps: dataset code meanings, pagination behavior, and result shape are all unaddressed. For a supposedly 'bounded' search this is materially incomplete.

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 0%, so the description must compensate and does not. It names document-ID prefix, dataset, and classification as lookup keys, mapping loosely to three of five parameters, but never explains the opaque numeric dataset codes (1, 3, 8, 9, 10, 11, 12) or the category enum values, and says nothing about limit/offset 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 and resource ('Find bounded public document metadata') plus the lookup keys (document-ID prefix, dataset, source classification). This distinguishes it reasonably from the read_* siblings by implying a filtered search rather than a direct fetch, though 'bounded' is left unexplained.

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 exclusions ('No person search or removed-text passages') give useful scope boundaries on when not to use it. However, there is no explicit statement of when to prefer this over read_document_metadata, nor any prerequisites or conditions for choosing among siblings.

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