DaedalMap Administrative Boundaries (loc_id to polygon)

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

The readOnlyHint annotation already establishes safety, and the description adds meaningful behavioral nuance: historical geometry is the primary result, a current successor is only an explicit follow-up, and the call is a fast shape-only preflight. It also notes no payment is required, which is useful beyond the annotation.

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?

Five short sentences, each earning its place: what it does, what it reports, primary-result behavior, exclusions, and when to use it. The most decision-relevant information is front-loaded.

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 simple read-only preflight with two documented parameters and no output schema, the description is complete. It tells the agent what is returned, what is not returned, when to call it, and what constraints apply to the input.

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 schema already documents both parameters clearly. The tool description adds the 'bounded' qualifier and reinforces the single-vs-list choice, which helps an agent select the correct argument shape without opening 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 action ('shape-only preflight'), a specific resource ('geometry availability'), and the exact unit of work ('one loc_id or a bounded loc_id list'). It also distinguishes itself from sibling tools by explicitly saying it does not resolve points or explain other identity relationships.

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 clear usage context: 'Use before get_geometry or an export.' It also signals when not to use it by excluding point resolution and identity-relationship explanation. It does not explicitly name the alternative tools for those excluded behaviors, so it stops just short of fully explicit routing.

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 include readOnlyHint=true, and the description adds conditional behavior ('when approved geometry exists') and the caveat about point-chain seams. It does not contradict annotations and provides useful context beyond the read-only hint.

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 sentences, front-loaded with the core purpose. The inclusion of 'No payment required' is slightly extraneous but does not significantly harm clarity.

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 complex tool with 9 parameters and no output schema, the description covers key return values and usage context. It lacks explicit mention of batch usage via the 'items' parameter, but the schema covers that. It is otherwise quite 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%, so the schema already documents all parameters. The description adds no additional parameter-level detail; 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?

The description clearly states the tool's function: 'Detailed relationship tool for two geographic identities' and lists specific outputs (temporal validity, successor context, topology, geodesic intersection area, overlap shares). This distinguishes it from sibling tools like get_geometry or resolve_point.

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?

Provides explicit usage context: 'Use this after a compact point lookup' and directs to 'Use resolve_reference first for names or outside identifiers.' Also gives a critical caveat: 'A point-chain seam is not proof of strict parentage.'

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 provide readOnlyHint=false, leaving the description to carry the burden. It discloses synchrony, response budget, service-item caps, and environment-dependent behavior (hosted vs local loopback). This is substantial behavioral context beyond what annotations offer.

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 core action, then scaling limits and redirection. Every sentence contributes value without repetition or 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 create/export tool with no output schema, it covers purpose, limits, access lane, and formats. The only notable omission is the return value or response structure, which is a minor gap given the tool's nature.

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 38% (3 of 8 params described). The description compensates by clarifying that loc_ids are an exact list with a default cap of 250, scope must be a single strict scope, format maps directly to the enum, and quote_id originates from estimate_geometry_package. Some optional params like include_polygon and output_name remain unexplained, but the core selection params gain meaningful context.

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 clearly states it 'Creates a synchronous v0 geometry export' from 'exact loc_ids or one strict scope', with explicit format options (GeoJSON, gzipped GeoJSON, zipped GeoJSON). This specific verb-resource pair distinguishes it from sibling tools like get_geometry (retrieval) and create_conversion_job (asynchronous conversion).

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?

Provides clear operational guidance: hosted service default of 250 loc_ids, 10-20 second response budget, and direct local-loopback exception. It explicitly directs users to estimate_geometry_package or get_tool_help for the effective access lane. However, it doesn't explicitly contrast with async alternatives like create_conversion_job, so not a full 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 declare readOnlyHint=true, and the description reinforces this with 'Dry-run' and 'estimates an export artifact'. It adds valuable context by disclosing exactly what the estimate covers (loc_id count, shape/vintage availability, bytes, delivery mode, citation requirements, charge units) and explicitly excludes canonical release bundles. No contradictions or hidden side effects are indicated.

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 two sentences, front-loaded with the core purpose ('Dry-run estimate for a selected geometry export') and followed by a clarifying exclusion. Every word adds value—no filler or redundancy. It is highly concise and effectively structured.

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 read-only tool with a rich schema and no output schema, the description adequately covers the purpose, output contents, and scope exclusions. It does not explicitly explain the input selection methods (e.g., loc_id vs. scope) but the schema covers that. Given the tool's moderate complexity and high schema coverage, the description is complete enough, though it could benefit from a direct pointer to sibling tools like create_geometry_export for contextual flow.

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 high (86%), so the parameters are mostly self-explanatory from the schema. The description does not add additional parameter-level semantics beyond what the schema provides; it focuses on the output of the estimate rather than input parameter details. This meets the baseline for high schema coverage.

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 clearly states the tool's function: 'Dry-run estimate for a selected geometry export' and specifies the exact outputs (loc_id count, shape/vintage availability, bytes, delivery mode, citation requirements, charge units). It also differentiates from a 'canonical DaedalMap geometry release bundle', distinguishing this estimation tool from other geometry-related tools in the sibling 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?

The description effectively implies when to use this tool: when a dry-run estimate is needed before a geometry export. It provides context by naming specific estimate dimensions and clarifying it is not a canonical release bundle, but it does not explicitly name alternative tools or state 'use this instead of X'. The guidance is clear though not fully explicit.

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, so the description's focus on 'Returns the list' does not contradict that or add much beyond the annotation. The phrase 'live agent-ready data packs' adds context about what data is available, but does not disclose additional behavioral traits such as pagination, rate limits, or response structure.

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 a single, clear sentence that communicates purpose and key context ('Free discovery', 'live agent-ready data packs') without wasted words. It is appropriately sized for the tool's simplicity.

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 parameterless, read-only listing tool, the description adequately states what it returns and the domain (DaedalMap). There is no output schema, but the return type ('list') is stated. Combined with the sibling context, this is sufficient for an agent to select and invoke the tool 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?

The tool has zero parameters, so the description does not need to explain parameter semantics. The schema already documents this fully (schema description coverage 100%), and the baseline for zero-parameter tools is 4.

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 uses a specific verb ('Returns') and resource ('list of live agent-ready data packs available on DaedalMap'), clearly distinguishing it from siblings like get_pack and query_dataset. The 'Free discovery' phrase clarifies it's a zero-cost listing operation.

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 use for discovering available data packs ('Free discovery'), but does not explicitly state when to use this tool versus alternatives like get_pack or query_dataset. It provides some contextual hint but lacks explicit when-to-use or when-not-to-use 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 provide readOnlyHint:true, and the description adds significant behavioral detail beyond that: historical geometry is returned first, an evidenced successor is never substituted or fetched automatically, and no payment is required. This discloses behaviors an agent could not infer from annotations 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?

The description is front-loaded with the core purpose and remains efficient. Every sentence adds value: scope, return contents, historical behavior, sibling routing, polygon guidance, and payment status. No word is wasted.

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 lists the returned components and key behavior. It does not describe response envelope, error cases, or whether loc_id and loc_ids can be combined, but for a read-only geometry retrieval tool this is a minor gap given the schema already documents parameters.

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 adds extra meaning by clarifying that loc_ids can come from any level of a resolve_point chain and by advising when to request the polygon versus bbox/centroid. This goes beyond what the schema properties state.

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 opens with a specific verb and resource: 'Shape retrieval for exact loc_ids,' and states exactly what is returned (metadata, vintage, centroid, bounding box, optional GeoJSON polygon). It also differentiates from siblings by noting that hierarchy and crosswalk details belong to loc_id_info.

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 gives explicit routing guidance: use loc_id_info for hierarchy/crosswalks, and prefer bbox/centroid unless exact rendering or clipping requires the polygon. This provides clear when-to-use and when-not-to-use context relative to alternatives.

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 readOnlyHint=true, and the description adds useful behavioral context by specifying that only completed inline jobs are retrievable under the current public contract, while durable queued jobs and downloadable artifacts remain unsupported. This enriches the annotation without contradicting it.

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 two sentences: the first states the core action with precision, the second provides a clear contract limitation. No unnecessary words or redundancy.

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 simple read-only status tool with full schema coverage and a read-only annotation, the description is largely sufficient. It covers purpose and contract limitations, but the lack of an output schema means a brief note on return value would be useful, and the term 'bounded v0' is somewhat cryptic.

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%, setting a baseline of 3, but the description adds meaning by requiring job_id to be a completed 'bounded v0' job, which goes beyond the schema's simple origin reference and clarifies expected job state. request_id is already well-documented in 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?

The description uses the specific verb 'Retrieves' and clearly identifies the resource as 'completed bounded v0 geometry export or conversion job' accessed 'by job_id'. This distinguishes it from sibling creation/estimation tools such as create_geometry_export and create_conversion_job.

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 for retrieving completed inline jobs and explicitly notes that durable queued jobs and artifact links are future capabilities, which sets expectations. The schema also references create_geometry_export and create_conversion_job as job_id origin points, but the description itself does not explicitly state when to use or avoid this tool relative to alternatives.

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?

The readOnlyHint annotation already covers the safety profile, and the description adds useful context about what will be returned (metadata, coverage, freshness, examples). It does not disclose any additional behavioral traits such as rate limits, authentication needs, or side effects, but none appear necessary for this read-only discovery 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?

The description is compact, well-structured, and front-loaded with the core purpose ('Free discovery'). Each sentence contributes value: the first states what it returns, the second tells when and why to call it.

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 a single parameter, full schema coverage, and a read-only annotation, the description provides enough context for correct invocation. It explains the output categories and the recommended usage scenario, though it stops short of detailing exact return fields or potential 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?

Schema description coverage is 100%, so the schema already documents pack_id sufficiently. The description adds context that the pack is identified from get_catalog, but does not meaningfully extend the parameter semantics beyond what the schema provides.

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 clearly states the tool returns detailed metadata, coverage, freshness, canonical tool guidance, and first-query examples for one pack. It distinguishes itself from the sibling get_catalog by emphasizing 'one pack' and positioning itself as a pre-query discovery step.

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 gives explicit guidance to call this tool before querying a new pack, explaining the value (time shape, coverage limits, paste-ready first query). It does not explicitly mention alternatives or when not to use it, but the directive is clear and contextually sufficient.

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?

Beyond the readOnlyHint annotation, the description reveals the tool returns refusals, access limits, provenance fields, and a shared interaction contract. This provides substantial insight into the tool's behavior and the nature of its responses.

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 two sentences with no filler. It front-loads the purpose, then lists specific output types and usage instructions, achieving maximum information density.

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 tool with readOnlyHint and no output schema, the description covers purpose, usage context, input source, and the types of information returned. It is comprehensive and leaves no critical gaps.

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 input schema already fully documents the sole parameter, tool_name, specifying it must be an exact name from tools/list. The description reinforces this workflow but adds no additional semantic detail beyond what the schema already covers.

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 clearly states the tool's purpose: providing guidance for using another tool on the MCP facade. It enumerates specific outputs (when to use, refusals, example, limits, etc.), making it distinct from sibling data-access tools.

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 provides explicit usage guidance: call this before working with an unfamiliar tool, and use tools/list to discover tool names. It lacks an explicit statement of when not to use it, but the context strongly implies it is only for unfamiliar tools.

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 provide readOnlyHint=true, but the description enriches the behavioral picture considerably: supersession is never automatically substituted, historical records are only returned as requested, and parent edges are never invented across mixed releases. It also discloses the 'No payment required' policy, which is useful operational context beyond the annotation.

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 dense yet well-structured: it opens with the tool's role, then input modes, then output contents, then flag semantics, then sibling differentiation and alternatives. Every sentence contributes distinct information, and the text stays readable despite covering a complex 11-parameter 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?

Given 11 parameters and no output schema, the description covers the essential context: how to supply inputs, what the key flags do, what output categories to expect, and when to use sibling tools. The behavioral constraints around supersession and mixed releases are also included. Nothing critical for a correct first call appears to be 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, but the description adds semantic depth beyond individual property docs. It explains the relationship between loc_id and loc_ids, clarifies that include_hierarchy returns the 'strict same-release ancestor chain', and ties include_references to external crosswalks. This helps an agent understand parameter intent, not just types.

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 uses a specific verb and resource: a 'drill-down tool for loc_ids' that retrieves metadata, parentage, shape status, vintage/lifecycle fields, and child counts. It further distinguishes itself from siblings by noting 'resolve_point intentionally stays compact' and naming get_geometry and compare_geographies as alternatives. The purpose is unambiguous and clearly differentiated.

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 explicitly states when to use the tool: pass one loc_id or the stack loc_ids from resolve_point, and enables hierarchy/references via flags. It also gives clear exclusion guidance: 'For exact polygons use get_geometry, and for overlap or successor analysis use compare_geographies.' This leaves no ambiguity about when to select this tool versus alternatives.

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?

Beyond the readOnlyHint annotation, the description adds behavioral constraints: 'strict hierarchy traversal', 'coherent parent chain', and 'must not bridge release seams.' It also clarifies that 'No natural-language decoding is performed,' which is valuable context for callers. These details significantly enrich the safety and usage profile.

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 sentences, each earning its place: function, non-goals, use case, and a behavioral caveat. No redundant or promotional language. The description is front-loaded with the core purpose and immediately gives actionable context.

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 tool has nested scope objects and 8 parameters, but the schema already documents them well. The description explains the core use case and exclusion behavior. It could optionally mention output structure, but the schema's mention of 'rows', 'counts', and 'limit' covers that. Slightly more could be said about when the scope object is preferred, but overall sufficient.

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 high (88%) with informative descriptions for parent_loc_id, admin_level, limit, count_only, etc. The description reinforces the key parameters by naming them ('parent loc_id and target admin level') and adds the no-NL note, which clarifies that admin_level expects structured values. This is a slight value-add 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?

The description states a specific verb and resource: 'returns descendants from that coherent parent chain' given a parent loc_id and target admin level. It distinguishes itself from the 'mixed-vintage latest-per-depth point resolver' (likely resolve_point), making its purpose unique among siblings.

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 when to use: 'Use it before shape exports such as every county in a selected parent scope.' Also states what it is not: 'not the mixed-vintage latest-per-depth point resolver' and 'must not bridge release seams.' This gives clear guidance on alternatives and placement in workflows.

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