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

Annotations cover only readOnlyHint and openWorldHint, so the description carries the rest and does so well: it discloses latency expectations ('Typically 1-3 s'), the failure mode and threshold ('fails with query_timeout after 30 s'), and the exact pagination protocol (which fields to send when column_cursor is present). These are non-obvious operational traits an agent cannot infer from 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?

Front-loaded with purpose, then prerequisites, then parameter guidance, then an example, then performance. The opening sentence is a dense colon-list and the illustrative JSON adds bulk, but every sentence supplies decision-relevant information rather than restating the schema.

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 values need no prose. With annotations covering safety and the description covering triggers, pagination, latency, failure mode, and the area-question special case, an agent has everything needed to call this correctly on the first attempt.

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; the description goes beyond it by tying detail="full" to area questions, explaining the column_cursor calling convention, and clarifying that column filtering matches name or description. It does not, however, mention sample_rows semantics, which the schema does cover, so 4 rather than 5.

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?

Opens with a specific verb+resource+decision framing ('Decide whether and how to query a dataset') and enumerates exactly what is returned: columns, live row count, data_coverage, place fields with reliability, geo columns. This clearly separates it from atlas_query_dataset (executes queries) and atlas_search_datasets (finds datasets).

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?

Explicitly states the trigger condition ('Call before querying a dataset whose columns you do not know') and a conditional branch ('For area questions, use detail="full"'). It also gives a correctness rule that prevents a common error ('Filter a place field on its `value`, never its label'), which is when-to-use guidance of the most actionable kind.

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 readOnly/openWorld, but the description adds nontrivial behavior: empty candidates list is not an error, results are ordered by match alias/name/place_name/host then tier then id, pagination requires sending cursor alone, and no network call is made. These are exactly the traits annotations cannot convey.

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-loaded with the purpose and the portal-id contract, then constraints in order of use. Dense and slightly choppy ('told apart by jurisdiction.level'), but nearly every line carries 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?

For a 6-param, zero-required lookup with an output schema, the description covers the pieces the schema cannot: ambiguity handling, ordering, pagination discipline, empty-result semantics, and the fact that the registry is local. Nothing an agent needs 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 coverage is 100%, so the baseline is 3; the description still earns credit by adding a cross-parameter constraint ('With cursor, send only cursor and optionally page_size') and a concrete invocation example, which the per-parameter schema text cannot express.

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 portals by place name') and adds the tool's role in the workflow: the returned id is what every other tool's `portal` parameter expects, which separates it from the dataset-oriented atlas_* siblings. An agent immediately knows what this returns and why it matters.

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?

Explicit precondition: 'Call this before any tool that takes `portal` when you lack its id.' It also gives disambiguation policy — when candidates differ in jurisdiction.level, ask the user unless the request already specifies — so the agent knows what to do with ambiguous results.

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 and openWorldHint=false, so the safety profile is covered. The description adds behavioral context the annotations don't: index-by-default behavior and the argument-repetition protocol across paginated calls.

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, front-loaded with the purpose and content list, followed by the default-call rule and a compact example. No filler, and the most important guidance arrives first.

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-format explanation is unnecessary. Between the description (what the reference covers, index default, pagination protocol) and the schema (topic enum, portal constraints), an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3, but the description adds real value beyond it: a concrete example pairing topic and item_id, and the non-obvious pagination rule that on subsequent pages you repeat only topic and (for guides) portal.

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 (the server's reference) and enumerates exactly what that reference contains: capabilities, portals, guides, SoQL help, errors, tiers. This clearly distinguishes it from the dataset-oriented siblings (atlas_query_dataset, atlas_search_datasets, atlas_find_portals).

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 concrete invocation guidance: no arguments yields the index, and a worked example shows topic/item_id usage. It stops short of routing the agent away from overlaps with atlas_find_portals (topic=portals) or atlas_describe_dataset, so usage is clear but not fully disambiguated.

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 cover the safety profile (readOnlyHint, openWorldHint), and the description adds substantial behavior beyond them: the 10,000-row paging cap, typical 1-5 s latency, failure mode query_timeout after 30 s, and the cursor protocol requirement to repeat portal (confirmed also in the schema). This is exactly the kind of operational context an agent needs before committing to a call.

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 its bound, then layers routing rules, the cursor-only parameter subset, the download escape hatch, and a compact illustrative call. Every sentence carries distinct information and the worked example is the densest way to convey the group_by/order_by idiom.

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 14-parameter tool with an output schema and full schema coverage, the description supplies what the schema cannot: the paging ceiling, aggregate-vs-page routing, continuation-parameter discipline, download fallback, and timeout behavior. Return-value explanation is rightly delegated to the output schema.

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% across 14 params, so baseline is 3. The description goes further by stating cross-parameter rules the schema only implies per-parameter: which fields to send on a cursor continuation, and that aggregates should use count(*) with group_by rather than paging. It doesn't cover the soql/near/search_text modes at all, so not a 5.

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+resource ('Run a bounded read or aggregate on one dataset') and adds the hard scope limit (paging stops at 10,000 rows). It does not name or contrast against any sibling (atlas_describe_dataset, atlas_search_datasets), so the agent must infer that this is the query/aggregate tool rather than the discovery or metadata tool.

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: aggregates via count(*)+group_by instead of row paging, send only portal/dataset_id/cursor plus optional page_size or detail on continuations, and give the user download_url with detail='full' rather than paging all rows. These are concrete when-to-use and when-not-to-paging instructions, not vague hints.

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?

Goes well beyond the readOnly/openWorld annotations: results are candidates, match_evidence discloses which query words the metadata lacks, only queryability 'supported' entries can be described or queried, tabular searches may add up to 3 non-queryable external_matches, and latency is 'typically 1-3 s.' This is exactly the downstream-behavior context annotations cannot 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?

Front-loaded with purpose and trigger, then the candidate/queryability caveats, then a minimal example and latency note. Dense but nearly every clause carries information; the phrasing around external_matches ('which cannot') is slightly compressed but not wasteful.

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 values need not be restated, yet the description still surfaces the two result fields an agent must interpret (match_evidence, external_matches). Combined with the paging hint and portal-id sourcing, nothing needed to call this 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 already 100%, so the baseline is 3. The description earns extra credit by explaining the operational consequence of asset_scope (federated/external links 'cannot' be queried) and by showing a concrete call shape ({portal, query}). It does not add syntax detail for cursor, page_size, or detail beyond 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 and resource ('Find a portal's datasets by topic') and immediately distinguishes itself from id-based siblings with 'Call when you lack a dataset id.' An agent can route here versus atlas_describe_dataset or atlas_query_dataset 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 when you lack a dataset id' gives an explicit trigger condition that separates this from the id-requiring siblings. It also implicitly points to atlas_find_portals for the portal id (reinforced in the schema). It stops short of stating when *not* to use it or naming the alternatives directly.

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