UNESCO UIS — Education, Science & Culture Statistics (provenance-first)

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

Annotations already declare readOnlyHint and idempotentHint; the description adds beyond that by explaining the live GET behavior against the public source and the error condition for unknown ids. This gives the agent practical expectations without contradicting the 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?

The description is front-loaded with the primary action and return contract, followed by domain context, error behavior, and routing guidance. Each sentence provides distinct value, though the catalog context sentence adds length and 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 one-parameter fetch tool with an output schema, the description covers the return shape, id provenance, error behavior, behavioral traits, and sibling distinctions. Nothing needed for the agent to invoke 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% with the id description, so the baseline is 3. The description adds meaningful extra context by stating that only ids from `search` are valid and that an unknown id errors, reinforcing validation rules beyond the schema's simple field description.

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: 'Returns the full document for an id obtained from `search`', and details the exact return shape ({ id, title, text, url, metadata }). It also distinguishes itself from the `uis_*` data query tools, so an agent can immediately tell this is the document-retrieval companion to `search`.

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 that only ids returned by `search` are valid and that unknown ids return an error, giving clear input constraints. It also directs data queries to the `uis_*` tools, providing an unambiguous 'when not to use this tool and what to use instead' 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?

Although read-only and idempotent are already in annotations, the description adds valuable behavioral detail: up to 10 results, relevance ordering, empty list meaning no match, and the fact that the catalog comes from a public source and is cached in memory. This goes well beyond the 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?

The description is front-loaded with the core behavior and return format, then efficiently covers contract context, alternatives, query expectations, and behavior in separate short sections. Each sentence adds practical value.

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 catalog search tool, the description is complete: it defines the result contract, ordering, empty-result behavior, language support, and how to continue the workflow via `fetch`. Nothing invocation-critical 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?

The schema already fully documents the `query` parameter, so the baseline is 3. The description adds meaningful extra context by specifying supported languages ('Portuguese or English') and reiterating that natural language or keywords are acceptable.

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 a specific verb ('Searches'), a specific resource ('UNESCO UIS statistics catalog'), and the exact result shape ('{ id, title, url }'). It also differentiates itself from the uis_* tools by calling itself 'a catalog index, not a data query.'

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 explicitly tells the agent when to use this tool versus alternatives: pass returned ids to `fetch`, and prefer `uis_*` tools for direct data questions. This is highly actionable and leaves no ambiguity about tool selection.

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 readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: values are returned raw and untransformed, and oversized queries are rejected with the record count rather than truncated. It stops short of describing pagination or any result-size cap on accepted queries.

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 the resource and filters before the constraints and caveats. Every clause carries information; the only cost is that the raw-records and ILOSTAT disclaimers are stacked into one long sentence, slightly diluting scannability.

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 explanation. Combined with annotations covering the safety profile and a 100%-documented schema, the description supplies the remaining essentials: where codes come from, the 25-indicator ceiling, raw/unaggregated output, and the rejection behavior for broad queries.

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 a baseline of 3 applies, and the description goes beyond it by tying 'indicators' to uis_search_indicators with a max of 25 and 'geo_units' to uis_list_geo_units, plus explaining what include_footnotes yields. It adds cross-tool provenance but no syntax detail for year bounds beyond what the schema already shows.

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 ('statistical records from the UNESCO Institute for Statistics Data API') and immediately scopes it by the three filter axes. It also distinguishes itself from siblings by naming uis_search_indicators and uis_list_geo_units as the code sources, and by ruling out the ILOSTAT MCP server's data.

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 prerequisites (codes must come from uis_search_indicators / uis_list_geo_units) and operational guidance ('narrow by geo unit or years' when broad queries are rejected). It does not, however, contrast this tool with the generic 'fetch' and 'search' siblings, so routing between those remains implicit.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context beyond the annotations: the size of the result set (462 units) and the important scope constraint that these codes apply only to uis_get_data, not other statistical servers.

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 with no filler, and the most important facts — what the codes are and where they apply — are front-loaded. Every clause carries information an agent needs.

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, the return format needn't be explained, and the description still clarifies that no statistical values are returned. For a low-complexity lookup tool with full parameter documentation and annotations, 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 description coverage is 100%, so all five parameters (type, limit, offset, search, provenance_mode) are already documented, including the NATIONAL/REGIONAL enum and the search-by-name-or-code semantics. The description's 'Filter by name/code and type' merely restates what the schema provides, 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 names the specific resource (462 UNESCO UIS geographic codes) and its exact role: supplying valid codes for uis_get_data. It distinguishes its output from statistical data and explicitly scopes the codes to uis_get_data rather than other statistical servers, so the agent can separate it from siblings like uis_get_data and uis_search_indicators.

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 frames the use case — resolving valid geographic codes before calling uis_get_data — and states what the tool does not do (return statistical values). It stops short of an explicit 'call this first to resolve codes' instruction or direct comparison with siblings, but the context is unambiguous.

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 readOnly/idempotent annotations, the description reveals AND semantics, case-insensitivity, vocabulary normalization to UIS terminology, the response's vocabulary_notes field, and the return of data-availability metadata. This substantially enriches the agent's expectations beyond what annotations alone 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?

Four dense, front-loaded sentences with no filler. Every sentence contributes either scope, matching semantics, vocabulary behavior, return content, or routing to alternatives, and the purpose appears immediately in the first sentence.

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 search tool with a rich schema and output schema, the description covers what the tool searches, how matching behaves, how vocabulary is normalized, what the response contains, and how the tool relates to its key siblings. Nothing essential for correct invocation 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?

The input schema already documents all 5 parameters fully, so the baseline is 3. The description adds meaningful semantics for query matching (AND, case-insensitive, vocabulary resolution) and mentions optional theme filtering, going beyond the schema's simple field descriptions.

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: searching the UNESCO UIS catalogue of ~5,000 indicators by keyword in name or code with optional theme filtering. It links to uis_get_data as the downstream consumer of results, which clearly distinguishes it from 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 directs users to uis_get_data for statistical values and to the ILOSTAT server for ILO labour data, establishing when not to use this tool. It also gives practical search strategy guidance: start with 2–3 terms and drop terms if 0 results.

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