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

With no annotations, the description carries the full burden and does so: one polite request, redirects reported rather than followed, bot blocks surfaced rather than circumvented, and a hard limit on which sources it will touch. These are exactly the side-effect and policy details an agent needs before invoking.

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 and then the behavioral constraints, with no filler. Every clause conveys either an output or a limit.

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?

Covers the return values (status, timing, redirects, registry agreement) and the safety posture well, which is what matters for a read-only check with no output schema. The only real gap is the identifier semantics for the three-parameter 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?

Only the url parameter is documented in the schema (33% coverage), and the description says nothing about source_id or registry_id. With three optional identifiers and zero required parameters, the agent is left guessing whether url, source_id, or registry_id alone suffices or whether they must be combined.

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 scope ('Live check of one source's portal URL') plus the exact outputs it produces (redirects, HTTP status, response time, registry match). The word 'live' separates it from the static discovery siblings like find_sources and registry_info without needing to name them.

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 'live check' framing implies the use case (verify a portal is reachable and consistent with the registry), and it gives a concrete exclusion: it never calls key-required or account-gated sources. It stops short of explicitly routing the agent away from siblings such as registry_info for stored status.

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 of disclosure. It does disclose a genuinely important behavioral trait: matching uses a curated key-column map rather than raw column-name equality, so results reflect a normalization layer. However, it never states that this is a read-only operation, says nothing about how large or expensive the scan is, and does not describe error behavior when the dataset_id is invalid.

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, zero filler. The primary purpose comes first, and the list of keys and the curated-map caveat follow as supporting detail. Nothing could be removed without losing 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 three-parameter read tool with no annotations and no output schema, the description covers the core semantics and the key taxonomy. What is missing is a sense of what a result entry looks like beyond 'grouped by key' and whether limit_per_key applies per group. That roughly matches the expected baseline, but it is not complete for a dataset-discovery tool.

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 67%; the dataset and column parameters are documented in the schema. The description adds real meaning by enumerating the recognized key labels (BBL, BIN, borough, census tract, FIPS, ZIP, and so on), which clarifies what 'column' will accept. It says nothing about limit_per_key (which the schema also leaves undocumented) or about how a field name differs from a key label in practice.

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-plus-resource construction: it returns datasets that share a join key with a given dataset, and it explicitly says the results are grouped by key. That is far more precise than its name 'find_joinable' alone. It does not name a sibling such as search_datasets or find_sources to contrast with, but the purpose is unmistakable.

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 phrase 'share a join key with this one' implies the use case, which is finding datasets you can join against the supplied dataset. The description gives no explicit when-to-use or when-not guidance, and it does not say to call it instead of, or after, get_dataset_columns or search_datasets. The descriptors in the input schema (dataset_id, Socrata 4x4, ArcGIS item id or URL) support the guidance that already exists implicitly.

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 supplied, the description carries the full burden and does a fair job: it lists the return shape (portal URL, platform family, API type, dataset count, status, last-verified date) and flags the non-obvious default of status='live'. It omits authentication requirements, rate limits, pagination behavior and whether 'any' materially changes result volume, which are the remaining gaps.

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, all front-loaded: what it finds, what it returns, what it does not search, and the default filter. No redundant restatement of the tool title and 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 an eight-parameter search tool with no output schema, the description supplies enough to call it correctly: return fields, search scope, the default status filter, and the sibling to use for datasets. Minor incompleteness remains on the two undocumented enum parameters and on limit/pagination semantics.

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 75%, so the baseline is 3; the description earns a bump by clarifying the query parameter's actual search scope (portal names and notes rather than dataset titles) and reinforcing the status default. It adds nothing for key_required or platform_family, which are also undocumented in the schema, leaving those enums unexplained.

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 gives a specific verb and resource — finding New York open data portals/sources in BetaNYC's registry — and enumerates the source types covered (state, county, city, agency, library, nonprofit). It explicitly distinguishes itself from search_datasets by noting it searches portal names and notes, not dataset titles.

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 clearly states the intended search surface (portal names and notes) and routes the agent to search_datasets when dataset titles are wanted. It also discloses that the default status filter is 'live', which affects results. It does not address the other siblings such as list_sources_for_place, so there is no exclusion guidance for those.

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 disclosure burden; it does add real content by distinguishing portal-sourced provenance from locally derived provenance, which is non-obvious. However, it never states that this is a read-only lookup, how large responses can get for wide datasets, or what happens on an unresolvable identifier.

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?

It is a single sentence with no filler, but it is an unstructured run-on list chained by 'plus' and 'and', which makes the main payload (columns) hard to separate from secondary metadata at a glance.

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?

There is no output schema, so the description must describe returns, and it does so fairly thoroughly across both schema-level and distribution-level metadata plus provenance. Missing are error/failure behavior and any note on response size for wide datasets.

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 already explains accepted identifier forms (dataset_id, Socrata 4x4, ArcGIS item id, URL). The description adds no additional meaning about the single dataset argument, so the schema does all the work.

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 (columns/fields for one dataset) and enumerates the payload: names, types, descriptions, distributions, license, publisher, extent, provenance. It is a noun-phrase inventory rather than a verb-first statement, and it does not name or differentiate itself from sibling tools such as search_datasets or check_source.

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?

There is no when-to-use guidance and no mention of alternatives. The only routing hint ('dataset_id from search_datasets') lives in the schema, not the description, and nothing tells the agent how this differs from check_source or find_sources.

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 and does well: it discloses that endpoints are copied verbatim and never guessed, names the data-quality flags emitted (UNCONFIRMED, undocumented, gated, dead, no-portal), and specifies the handoff target. It stops short of stating that this is a read-only lookup or whether any auth is needed to call the tool itself.

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 return contents are front-loaded in one dense sentence and the flags are called out in a short trailing fragment. It is information-rich with little waste, though the packed clause list is close to overstuffed.

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?

There is no output schema, and the description compensates by enumerating the returned fields and the flag vocabulary, plus naming the downstream MCP server and domain handling. An agent can decide and act from this, with only auth/read-only status left unstated.

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 entity, source_id provenance, and the registry_id rarity note. The description adds no parameter-level meaning beyond that, so 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 resource and enumerates exactly what the response contains (verbatim endpoint, API type, key requirement, example request, handoff server), which makes it distinguishable from find_sources and check_source. Slightly weaker because the name/opening frame it as 'how to query' rather than 'returns query instructions for one source'.

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 via the schema note that source_id comes 'From find_sources / list_sources_for_place results', which suggests a natural follow-up step. There is no explicit when-to-use versus check_source or registry_info, and no stated exclusions or prerequisites.

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 and does disclose meaningful behavior: it defines the three possible outcomes (has a portal, 'no-portal-exists', 'not-in-registry') and crucially explains that 'not-in-registry' means unchecked rather than absent — a distinction an agent would otherwise misinterpret. It does not cover response shape or ordering, but the state semantics are a real addition.

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 scope statement followed by the outcome semantics. Dense but every clause carries information; the parenthetical place-type list is slightly redundant with the schema examples 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?

The tool has no annotations and no output schema, so the description must explain what comes back — and it does, listing the four categories of sources and the three status outcomes. Only minor gaps remain, such as output structure or whether results are grouped by category.

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 schema examples already cover county, city, borough, and region forms, so the description's mention of those place types largely restates existing schema information. It adds only marginal meaning, such as implying that statewide sources can be excluded via the boolean parameter; 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 scope ("Everything the registry knows for one New York place") and enumerates exactly what is returned: the place's own portal(s), sources for cities inside it, regional sources, and statewide sources covering it. This makes the scope distinguishable in practice from a generic search tool, though it never names the closest sibling (find_sources) to draw the contrast 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 by the framing (look up all registry knowledge for a given place), and the place-type enumeration hints at accepted inputs. However, there is no statement of when to prefer this over find_sources or check_source, and no prerequisites or exclusions are given.

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 and zero parameters, the read-only nature is inferable but never stated. The mention of 'bundled or refreshed from GitHub Pages' usefully signals that the local copy may be stale, yet the description doesn't say whether calling triggers a network refresh, how long that might take, or what the return shape looks like.

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 sentence with no filler, and the primary content (row counts) is front-loaded. The semicolon-delimited list is dense and the ordering of secondary items is somewhat arbitrary, but nothing is redundant.

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?

There is no output schema, so the description carries the burden of explaining return values, and it does so field by field. The remaining gap is behavioral rather than definitional: the agent still doesn't know whether a refresh happens on call or what the response structure is.

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 schema has zero parameters, so there is no parameter semantics to explain; baseline 4 applies. The description correctly focuses its words on output contents instead of inventing input details.

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 enumerates concrete contents: row counts by status/tier/platform family, generation timestamp, provenance, unmapped platform strings, and harvest index size/date. That is specific enough to distinguish it from siblings like find_sources or check_source, which look up individual sources. It lacks an explicit verb ('returns'/'reports'), but the resource is unmistakable.

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: an agent can infer this is for checking registry coverage, freshness, or provenance, but there is no explicit when-to-use statement and no named alternative. It also doesn't say whether it should be called before querying sources to validate the data is current.

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 burden and does reasonably well: it discloses the harvested-index dependency, enumerates what each result contains (portal, link, formats, update date), and explains the Socrata-specific domain + 4x4 handoff to another MCP. It stops short of stating result ordering, default limit, or rate/refresh characteristics of the index.

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 dense sentences, front-loaded with what is searched and then what can be filtered on, with zero filler. The prerequisite and the cross-MCP handoff are packed into the same compact text rather than padded out.

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 7-parameter read tool with no annotations and no output schema, the description covers both input intent and return shape well enough to call it correctly. Minor gaps remain around result ordering, the default page size, and what happens if the index is empty or unharvested.

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?

At 71% schema coverage the schema already documents most parameters, and the description largely mirrors them (place, portal, platform family, format, last-updated). Its format enumeration is actually narrower than the schema's list, omitting json, arcgis, geopackage and pdf, so it adds little semantic value beyond the structured fields.

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 dataset titles, descriptions, tags and column names' — and bounds the corpus to harvested Socrata and ArcGIS portals in New York. It is clearly distinguishable from siblings like get_dataset_columns or find_sources, though it never names an alternative directly.

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 parenthetical '(needs the harvested index)' is a useful prerequisite an agent must satisfy before calling, and the filter list implies the intended discovery workflow. However there is no explicit when-to-use vs when-to-use-another guidance and no sibling is mentioned by name.

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 helpfully discloses the dual inclusion logic (index changes vs portal-reported updates) but omits limit/pagination behavior, ordering, return shape, and any permission/rate-limit context.

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, front-loaded with the selection criteria, and no unnecessary wording. The optional filter note is efficient.

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 3-parameter query tool with no annotations and no output schema, the description covers the core selection logic but omits the limit parameter and return/pagination details. It is adequate but not 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 coverage is 67%. The description clarifies 'since' as a date and 'portal' as an optional filter, but never mentions the 'limit' parameter, which has no schema description. It adds partial meaning but leaves one parameter undocumented.

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 resource (datasets) and the temporal scope (added, changed, removed since a date; portal-reported updates), so the purpose is clear. It does not explicitly distinguish itself from search_datasets or other siblings, 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 implies usage for finding recent index or portal changes and notes an optional portal filter, but gives no explicit when-to-use vs alternatives (e.g., search_datasets) or when-not conditions. Guidance is only implied.

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