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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered without the description. The text adds the verification-oriented intent but says nothing about auth, rate limits, or whether digests cover all published formats. Adequate, not rich.

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?

A single front-loaded sentence with no filler; the resource comes first and the motivating use cases follow compactly.

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 an output schema present, return values need not be described, and annotations cover the safety profile, so the description only needs purpose and usage — both present. Minor gap: it does not reinforce that the id must be versioned, though the schema handles that.

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 100%, and the schema already carries a detailed dataset_id note about versioned vs unversioned ids plus the format enum. The description adds nothing parameter-specific beyond what the schema provides, so the baseline 3 applies.

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 resource (published digests for one database file) and states the goal it serves, so an agent can tell it apart from list_databases, database_metadata and list_downloads. It is a noun phrase rather than a verb+resource construction, and it never names a sibling, so it falls 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?

It gives two concrete situations that select this tool: verifying a copy you already hold, and checking whether a build changed since the last fetch. That is clear usage context, but it does not state when NOT to use it or name the sibling that handles metadata/download listing instead.

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 readOnlyHint/idempotentHint/openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: the operation inspects without fetching, and the underlying files reach several GB, which is useful cost/size framing for an agent. It omits any note on latency or whether the sample rows are truncated, keeping it below a 5.

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 sentences, front-loaded with the return contents and then the use case; the em-dash clause about file size is the only embellishment and it earns its place by justifying the tool's existence. No filler or restatement of the title.

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 single-parameter, read-only inspection tool with an output schema present and rich annotations, the description covers what is returned, why to use it, and the cost tradeoff. Nothing needed to call it correctly is missing.

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 100% and the dataset_id schema text already spells out the versioned-vs-unversioned id distinction in detail. The description adds no parameter-level meaning at all, so the baseline 3 for high-coverage schemas is correct.

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 the specific resource ('one database') and enumerates exactly what is returned: columns per published format with types, sample rows, row count, build date, file sizes. That enumeration makes it unmistakable against siblings like database_checksum (hashes) and list_databases (catalog listing), so an agent can pick it without opening a schema.

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?

It gives a clear when-to-use with rationale: 'answer questions about what a database contains without downloading it - the files reach several GB - and to budget a transfer before starting one.' That implies the alternative (downloading) and two distinct intents, but no sibling tool is named as an explicit alternative, so it falls short of a 5.

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 cover the safety profile (readOnly, idempotent, openWorld), yet the description adds material context they cannot: answers are per-key and not identical across callers, so results should not be cached, plus the semantic decomposition of `standing` and the id-vs-base rule. This is exactly the kind of behavioral nuance only prose can carry.

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?

A single dense paragraph with no filler; the core statement (catalog, one entry per family) is front-loaded ahead of the `standing` and id guidance. It is slightly heavy for one block, but every clause carries operative detail rather than padding.

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?

Even though an output schema exists, the description supplies the interpretive layer an agent needs (what `standing` means, which id to feed downstream, why not to cache). Combined with the read-only annotations, nothing essential for correct invocation or use of the result is missing.

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 takes zero parameters, so the baseline is 4. The description's treatment of `versions[].id` vs `base` is about the response rather than inputs, so there is no parameter semantics to compensate for.

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 resource and verb: the IP database catalog as the API key's org sees it, one entry per database FAMILY. It goes further than a name restatement by defining the meaning of `standing` values and the `base` vs `versions[].id` distinction, so an agent knows exactly what comes back and how it differs from a generic catalog listing.

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?

It instructs the agent to call again rather than cache the result ('Ask again rather than holding on to this'), which is real usage guidance tied to per-key answers. It also routes the agent to pass `versions[].id` to 'the other tools', implying this is the discovery step before database_metadata/checksum. It stops short of naming those siblings as explicit alternatives or 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 declare only readOnly/openWorld/idempotency; the description adds the substantive behavior: refusals are included as rows, a denial populates `outcome` and `http_status`, results are ordered newest first, and the result set is a bounded window of at most 200 rows. That is real behavioral disclosure beyond the structured hints.

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 with no filler and the crucial 'refusals included' point front-loaded. The all-caps emphasis and the trailing window caveat make it slightly heavier than necessary, but every sentence carries information the agent needs.

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 an output schema present the description need not explain return fields, yet it still flags the two fields that matter for diagnosis (outcome, http_status) and warns about the window boundary. For a single-parameter read tool with annotations, nothing material is missing.

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 coverage is 100% and the single `limit` parameter is fully documented in the schema (range 1-200, default 50). The description only restates the 200-row window rather than adding format or interaction semantics for `limit`, so the baseline 3 is appropriate.

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 ('recent download attempts, newest first') and immediately scopes it to the caller's own organization. The inclusion of REFUSALS is spelled out, which separates it from list_databases and database_metadata siblings that deal with catalog objects rather than transfer attempts.

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 three concrete use cases ('explain a failing fetch', 'confirm a transfer ran', 'check whether a request was theirs') and a critical non-use condition: a database absent from the answer is not in this 200-row window, not proof it was never downloaded. That is explicit when-to-use and when-not-to-conclude guidance.

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