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

No annotations exist, so the description carries the full burden. It does add one genuinely useful behavioral trait — that row grain, counting guidance, and caveats are only present 'when a source pack documents it', so the agent knows the response shape varies. It says nothing about failure modes for a malformed dataset_id, permissions, or latency.

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, no filler, with the returned-content inventory front-loaded and the call-order directive closing it. Every clause earns its 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?

With no output schema, the description correctly takes on the job of enumerating return values, and the conditional clause handles the variability. The remaining gap is failure behavior — what happens when the dataset_id is invalid or the domain is unknown — which an agent would want before committing to the call.

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%, with all three parameters documented in detail, including that reporter_question must be the verbatim question. The description adds no parameter-level meaning of its own, 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?

States a specific verb ('Return') and an enumerated resource set: schema, source update time, row grain, counting guidance, and caveats. That inventory is distinct from what query_dataset or search_datasets would return, so an agent can route between them without opening any 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?

'Call this before writing a query' is an explicit ordering directive that ties this tool to the query workflow, which is real usage guidance. It stops short of naming query_dataset as the alternative or stating when the call can be skipped, so it is clear context rather than full when/when-not guidance.

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?

No annotations are provided, so the description carries the full behavioral burden. It does useful work by enumerating the snapshot payload (query, frozen rows, source update time, completeness, methodology, warnings) and hinting at a temporary-vs-pinned lifecycle, but it says nothing about what happens with an expired or invalid URI, permission requirements, or failure modes — significant gaps for a read tool whose only parameter is a URI that can go stale.

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 with zero waste: the action and scope come first, then the payload contents. Every clause carries information an agent can 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?

For a one-parameter read tool with no annotations and no output schema, the description does the essential job of describing what comes back. The remaining hole is behavioral — nothing about expiry, errors, or access requirements for temporary snapshots, which is the main risk an agent needs to know about.

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?

There is a single parameter with 100% schema description coverage, and the schema already explains that the URI is the one returned by query_dataset. The description adds no further syntax, format, or validation detail, so the baseline of 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 pairs a specific verb (Read) with a specific resource (temporary or pinned evidence snapshot) and states its purpose (for verification). It is clearly distinct from siblings like pin_snapshot and query_dataset, though it doesn't name those alternatives explicitly.

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?

Usage is only implied: 'for verification' suggests reading back evidence after a query, and the schema notes the URI comes from query_dataset, which establishes the workflow ordering. However, the description itself states no explicit when-to-use condition, no mention of expired/unknown URIs, and no routing away from siblings.

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?

With no annotations, the description carries the full burden: it discloses that each entry includes a last-checked date and that non-pack datasets yield a ROW GRAIN UNKNOWN warning, which is genuinely useful behavioral context. It does not cover result size, pagination, ordering, or auth/permission needs for a zero-param listing tool.

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 core purpose front-loaded and the warning caveat placed after. Slight redundancy in restating 'these packs', but nothing that fails to earn its 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 no-parameter, no-output-schema listing tool, the description conveys what comes back (portals, datasets, freshness dates) and the caveat attached to non-pack data. Only ordering/pagination expectations are unaddressed, a minor gap.

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 there is nothing for the description to disambiguate; the baseline 4 applies. No misleading parameter language is present.

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 (portals and datasets documented by a source pack) plus an attribute returned (last-checked date). It is clearly distinct from query_dataset/search_datasets by scope, though it never names a sibling explicitly.

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?

Usage is implied rather than stated: an agent infers this is the inventory/freshness lookup. The note that datasets outside packs remain queryable is useful context but is framed as a consequence, not as an explicit 'use X instead when Y' routing rule.

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?

No annotations are provided, so the description carries the full behavioral burden. It does disclose the key trait — a temporary snapshot becomes permanent/indefinite — but omits permissions required, what happens if the snapshot has already expired, and whether the pin is reversible.

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, both earning their place, with the action and durability effect front-loaded followed by the provenance hint. Nothing is padded, though it is terse enough that slightly more behavioral detail could have fit.

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?

A one-parameter, non-read-only action with full schema coverage and no output schema needs little prose, and the description covers the core effect. Missing only edge-case behavior such as expiry or permission failures, which is a modest gap rather than a blocking one.

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%, so snapshot_uri is already documented in the schema. The description only restates its provenance ('returned by query_dataset'), which is minor added value; baseline 3 applies when the schema does the heavy lifting.

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 (preserve/pin) plus resource (temporary query snapshot) and the resulting effect (indefinitely). The qualifier 'for a published story' narrows scope, and the mention of query_dataset clearly separates it from the retrieval sibling get_snapshot.

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 implies usage ('Use the snapshot URI returned by query_dataset') but never states when a caller should pin versus leave a snapshot temporary, nor does it mention any alternative or inverse operation. A usable hint exists, but the when/when-not decision is left 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?

With no annotations provided, the description carries the full burden and does so thoroughly: it discloses read-only behavior, row limits, success metadata, completeness/truncation semantics, presentation_rules, and failure behavior including isError=true and the error object fields. It also clarifies that failed queries produce no data result or snapshot.

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 front-loaded with the core purpose and then provides behaviorally important details about success, truncation, presentation rules, and failure. It is slightly dense, especially the long list of success response fields, but every sentence contributes operational information.

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?

The output schema exists and the description explains result and failure behavior well, but the tool has 8 parameters, no annotations, and low schema description coverage. The description is therefore complete on post-query behavior but thin on how to construct the query correctly.

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 only 38% across 8 parameters, so the description needed to compensate by explaining where, select, group_by, order_by, and max_rows. It only indirectly alludes to SoQL and a row ceiling; most parameter meanings remain undocumented beyond their names.

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 states a specific verb and resource: run a read-only SoQL query against a dataset, with a mandatory row ceiling. It clearly distinguishes this from sibling tools like search_datasets, describe_dataset, and get_snapshot, which handle discovery, metadata, and snapshots rather than row queries.

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?

Usage is implied by the query purpose and the note about handling truncated completeness, but the description does not explicitly say when to choose query_dataset over describe_dataset, get_snapshot, or search_datasets. It gives post-result guidance rather than tool-selection guidance.

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?

With no annotations, the description carries the full burden. It discloses two genuinely non-obvious behaviors: results flag whether a source pack documents them, and results do not carry quality/review/reliability/publication status. However, it omits return shape, pagination behavior, auth requirements, and rate limits, leaving meaningful gaps for a search tool.

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?

Four short sentences, purpose front-loaded, then scoping, then result semantics. No repetition of the name or title and no filler; the status caveat is a single clause that carries real information.

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 four-parameter search tool with no annotations and no output schema, the description covers purpose, domain scoping, and result caveats adequately. The main residual gap is that the return structure beyond the source-pack flag is unexplained, and no alternative-tool routing is offered.

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 only 50%, so the description must compensate — and it does so for the one genuinely ambiguous parameter by explaining that an empty domain searches every portal while a hostname scopes to one. search_term and limit (1-50, default 10) are self-evident, and reporter_question is well documented in the schema itself.

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 ('Search the Socrata catalog for datasets') and clarifies scope (all portals vs one). It implicitly separates itself from siblings like list_source_packs and describe_dataset, but never names them explicitly, so the differentiation is inferable rather than stated.

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 domain guidance ('Leave domain empty to search every portal, or give a portal hostname') is scoping help, not when-to-use guidance. The closing caveat about results lacking quality/review/reliability/publication status usefully signals a limitation, but the description never says when to prefer describe_dataset or query_dataset instead.

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