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

With no annotations, the description carries the behavioral disclosure burden. 'Find' implies a non-mutating operation, and the similarity mechanism is a useful behavioral detail. However, it does not explicitly state read-only behavior, or provide anything about data scope, performance, or side effects.

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, front-loaded sentence with no filler. Every word contributes either the purpose or the matching method, making it highly efficient for an agent reading 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?

The tool is simple, and the presence of an output schema reduces the need to describe return values. However, missing parameter semantics and no sibling differentiation leave the agent with only the minimal callable gist rather than full context.

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 0%, so the description must compensate. 'Find propositions related' implies that proposition_id is the seed for the search, but it never explicitly explains either parameter, and limit is completely unaddressed.

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 action ('Find propositions related') and the mechanism ('embeddings or Portuguese full-text similarity'), making the tool's purpose clear. It is reasonably distinguishable from siblings like search_propositions and get_proposition, though it never explicitly names them or contrasts with 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 description provides no guidance on when to prefer this tool over alternatives such as search_propositions or get_proposition. There are no prerequisites, exclusions, or typical use-case context; usage is only weakly implied by the verb 'Find' and the proposition_id parameter.

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 is the only source of behavioral context, but it only states that the URL is public and that the operation is a read of a release URL. It does not disclose whether network access is required, how missing assets are handled, or what the returned URL represents beyond being a download link.

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, tightly written sentence with no filler and the main action is front-loaded. It sacrifices some helpful detail, but as a concise statement it is well 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 simple two-parameter getter with an output schema, some missing context is tolerable, but the absence of any distinction from get_dataset_release and the lack of version semantics leaves a meaningful gap. The agent cannot fully determine when this tool is the right choice.

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 0%, so the description must compensate, but it only maps to asset_name via 'named dataset asset' and says nothing about the version parameter or the 'latest' default. An agent is left to infer that version is optional and has no semantics for how versions map to release tags.

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 ('Get') and resource ('public GitHub Release URL for a named dataset asset'), which clearly identifies the tool's function. It does not explicitly differentiate itself from the sibling get_dataset_release, so it stops short of full sibling-level clarity.

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 no indication of when to use this tool versus get_dataset_release or the other sibling tools. There are no alternative names, no exclusions, and no contextual conditions, so an agent has no guidance to select it correctly.

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 must carry the burden; it does signal a read-only retrieval operation and identifies the two artifacts returned. However, it does not explain how version selection behaves, whether any system state is read, or what 'coverage metadata' includes.

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 one compact sentence with the verb and object first and no filler words. It earns a high conciseness score even though the content could be richer.

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 is simple with one optional parameter and an output schema, so the description is not drastically incomplete. Yet it leaves release terminology, alternatives, and version semantics unexplained, which is a noticeable gap for an agent choosing among several dataset-related siblings.

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 has a single version parameter with 0% description coverage, and the tool description never mentions the parameter, its format, or how 'latest' is resolved. The description fails to compensate for the missing schema documentation.

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 ('Get') and target ('release manifest'), and additionally names what is returned ('coverage metadata'). It is clear but does not explicitly distinguish itself from the sibling get_dataset_download or define what a 'release' means in this domain.

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?

No guidance is given about when to call this tool rather than list_sources, get_proposition, or get_dataset_download. The context around release manifests is left entirely 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?

No annotations are provided, so the description carries the behavioral burden. 'Get' clearly implies a read operation, and 'canonical metadata and provenance' adds some context, but the description does not disclose behavior such as error handling, whether the UUID must be an exact canonical ID, or any data freshness/versioning considerations.

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 that front-loads the verb and resource with zero filler. Every word contributes meaning, and the description is appropriately sized for a one-parameter getter.

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 the simple input (one required UUID), the presence of an output schema, and no nested objects or enums, the description is sufficient for an agent to invoke the tool correctly. It clearly identifies what is returned and the expected identifier.

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 provides only a title for proposition_id with 0% coverage, so the description must compensate. It does so by specifying that the parameter is a proposition UUID, adding format and semantic meaning that the schema lacks.

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 ('Get'), a clear resource ('canonical metadata and provenance'), and a precise scope ('for one proposition UUID'). This distinguishes it from sibling tools like list_sources or read_proposition_text, which target different resources or operations.

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 the correct usage context: call this tool when you have a single proposition UUID and need its canonical metadata/provenance. It does not explicitly name alternatives or exclusions, but the singular-UUID scope provides clear context.

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; 'List' implies a read-only enumeration and the scope is described. However, it does not disclose whether authentication is required, whether all sources are returned, or any pagination/limitation behavior.

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, front-loaded sentence with no filler. Every word contributes to the tool's purpose and scope.

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 is a no-parameter list operation, and an output schema exists, so the description need not explain return values. The short definition is complete enough 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?

There are zero parameters, so the 0-parameter baseline of 4 applies; there are no parameter semantics the description needs to clarify.

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 'List' with the resource 'data sources' and names the returned dimensions (jurisdictions, licenses, redistribution status). This clearly differentiates it from the sibling tools, which focus on propositions and dataset downloads.

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 rather than explicit: an agent can infer this tool is for obtaining an inventory of available data sources. However, the description does not state when to use it over alternatives or provide any exclusion criteria.

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?

There are no annotations, so the description must carry the behavioral disclosure burden. 'Bounded page' does reveal that a call returns only a portion rather than the entire full text, and the offset/max_chars parameters in the schema reinforce pagination. However, it doesn't disclose page size limits, offset semantics, error behavior, or whether calls are safe/read-only, so the disclosure is thin.

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?

One short sentence that front-loads the core operation and omits filler. Every word earns its place and the structure is immediately scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and only three simple parameters, the description is near the minimum viable level, but it leaves pagination mechanics and usage context to be inferred. An agent could likely call it correctly by relying on parameter names and defaults, yet the description alone is not rich enough to feel complete for repeated paging.

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 0%, so the description must compensate for undocumented parameters. 'Bounded page' gives a rough idea that offset and max_chars control the window, but it doesn't define units, limits, defaults, or how to page sequentially. Parameter names are suggestive, but the description adds only general context rather than precise semantics.

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 ('a bounded page of a proposition's full text'), making it clear this is about fetching text content rather than metadata or summaries. The resource is concrete, but it doesn't explicitly distinguish itself from get_proposition, which could also serve text, so it stops 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?

The description implies use for reading chunks of long text, but it never states when to choose this instead of get_proposition or search_propositions, nor does it mention any exclusions or alternatives. No context about typical workflow or prerequisites is provided, leaving an agent to infer usage from name and schema.

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 must disclose behavior beyond the basic action, but it only rephrases the tool's function. It omits cursor-based pagination, how semantic similarity is computed or triggered, whether filters combine with AND/OR, and any read-only guarantee, leaving the agent guessing about execution details.

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, front-loaded sentence that efficiently establishes the tool's purpose. It contains no wasted words, but the brevity is partly responsible for the lack of detail in other dimensions.

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 9-parameter tool with no annotations and no schema descriptions, this description is far too sparse; it doesn't clarify expected value formats (year, house, state), pagination via cursor/limit, or whether semantic similarity requires a non-empty query. An agent cannot reliably select and invoke parameters from this text, even though an output schema exists.

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 0%, so the description had to explain the nine parameters, but it never maps 'identifiers', 'text', or 'filters' to specific fields such as query, year, house, state, author, municipality, proposition_type, cursor, or limit. This leaves the agent without meaningful guidance for constructing a valid search request.

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 clear action ('Search propositions') and names four search modes: identifiers, text, semantic similarity, and filters. It distinguishes from siblings like get_proposition and read_proposition_text, though it doesn't detail which identifiers or filter fields are supported.

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?

No sentences address when to use this tool instead of siblings; it never references get_proposition, find_related_propositions, or read_proposition_text, nor any conditions or exclusions. The verb 'Search' implies a discovery use case, but that is left entirely to inference.

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