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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), so the description earns credit for adding latency and failure behavior: 'Typically 1-3 s; fails with query_timeout after 30 s.' It also flags a non-obvious data caveat (place values vs labels, areas spanning multiple values), which is genuinely beyond structured fields.

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?

Front-loads the payoff, then usage rules, then an example and a performance note. Dense but every line carries decision-relevant information; the enumerated return list is a touch verbose but justified for a metadata tool.

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?

An output schema exists, so return formatting need not be explained. The description supplies everything an agent needs to decide whether to call it, choose detail, and interpret place fields, matching the tool's complexity.

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%, so the baseline is 3, but the description adds real decision semantics: when to set detail="full" (area questions) and how to use place fields (filter on value, not label). It also supplies a concrete example call.

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 (decide whether/how to query) and enumerates exactly what the tool returns: columns, live row count, data_coverage, place fields with reliability, and geo columns. The mention of querying clearly separates it from seattle_data_search_datasets and seattle_data_get_reference.

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 a clear trigger ('Call before querying a dataset whose columns you do not know') and conditional guidance ('For area questions, use detail="full"'), plus a field-filtering rule. It stops short of explicitly naming seattle_data_query_dataset as the next step or stating when this call can be skipped.

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=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context beyond that: the no-argument default returns the index, and the reference is organized into named sections that can be drilled into by topic/item_id.

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 plus a single example line; the content list is front-loaded and every clause carries information (what is retrievable, default behavior, worked example). No 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 an output schema present and zero required parameters, the description does not need to explain return shapes. It covers content scope, default behavior, and parameterization adequately; only an explicit pointer away from the dataset siblings would make it fully complete.

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 enum values are self-explanatory, so the baseline is 3. The description adds an illustrative example ({"topic": "soql", "item_id": "dates"}) that demonstrates the two-level topic→item lookup semantics, which is a genuine increment over the schema.

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 a well-scoped resource ('the server's reference'), then enumerates exactly what the reference contains: capability summary, SoQL help, dataset guides, and error catalog. This clearly separates it from the dataset-oriented siblings (search/describe/query), which operate on data rather than documentation.

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 with no arguments for the index' plus a concrete call example tells the agent how to enter the reference at two levels (index vs. specific item). It gives clear context for use but never explicitly contrasts itself with alternatives such as seattle_data_describe_dataset, so it stops short of 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?

Annotations only cover read-only and open-world status; the description adds the operational traits that matter: a 10,000-row paging ceiling, typical latency of 1-5 s, and a hard failure mode ('query_timeout after 30 s'). The cursor continuation constraint is a behavioral rule not derivable from the schema alone.

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?

Front-loads the core operation and row cap, then layers paging rules, an alternative path, a compact JSON example, and timing. Every sentence carries actionable information with no 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?

For a 13-parameter query tool with an output schema, the description covers the things the schema and annotations cannot: aggregation-vs-paging guidance, continuation semantics, row limits, and timeout behavior. Nothing an agent needs before invoking it 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%, so the baseline is 3; the description still adds value by constraining continuation payloads (only dataset_id, cursor, and optionally page_size or detail) and by pairing count(*) with group_by in the worked example.

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 ('run a bounded read or aggregate on one dataset') plus an explicit scope limit ('paging stops at 10,000 rows'). This cleanly separates it from the sibling search/describe/reference tools, which don't execute queries against a dataset.

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 explicit routing rules: use count(*) with group_by for counts and breakdowns rather than paging, and hand the user download_url with detail='full' instead of paging for all rows. It also states what to send on a continuation call with cursor, which is exactly the when/when-not guidance an agent needs.

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?

Adds substantial context beyond readOnlyHint/openWorldHint: match_evidence semantics, the fact that only 1-3 external_matches come back for tabular searches and are unusable, candidate-vs-confirmed result status, and a latency expectation (1-3 s). This is the kind of information an agent cannot get from annotations.

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?

Front-loads purpose and the when-to-use rule, then layers result semantics, an example, and timing in short clauses. Dense but every sentence carries information; the match_evidence/queryability sentences are slightly heavy for a first read.

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?

An output schema exists and the description still supplies the key result semantics (candidates, match_evidence, external_matches), plus when to call, an example invocation, and expected latency. An agent has everything needed to call it correctly and interpret the payload.

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%, so the baseline is 3, and the description earns a bump by showing query usage ({"query": "fire 911"}) and clarifying the behavioral consequence of asset_scope=tabular (external_matches returned but not queryable). It does not cover cursor/page_size, which the schema already documents.

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?

Specific verb+resource ("Find Seattle datasets by topic") with an explicit role in the workflow: "Call first when you lack a dataset id." That sentence alone separates it from seattle_data_describe_dataset and seattle_data_query_dataset, which both require an id.

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 a clear entry condition (no dataset id yet) and a downstream constraint (only queryability "supported" can be described or queried; external_matches cannot). It does not name the sibling tools it hands off to, so the routing is implied rather than explicit.

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