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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds behavioral context beyond annotations by explaining the 'found=false' return value for invalid IDs and the need for a prior search. This adds useful transparency.

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 concise: a single-line purpose, followed by structured XML tags for use case and important notes. Every sentence adds value, and the 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?

The description covers the input (ID), usage context (post-search), and error behavior (found=false). Since an output schema exists, return values do not need explanation. The description is complete for this tool's purpose.

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 provides descriptions for both parameters (business_id and language). The description reinforces the importance of the ID but does not add new semantics for the language parameter. With 0% schema description coverage in the context, the description partially compensates but misses the optional language parameter.

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 verb 'abrufen' (retrieve) and resource 'Details eines parlamentarischen Vorstosses', and the use case distinguishes it from the sibling tool 'parlament_search_business'. It is specific and action-oriented.

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: use after a search to get full details, requires the numeric business ID from search, and notes that 'found=false' is returned for unknown IDs. This clearly tells when and how to use the tool.

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 indicate readOnlyHint, idempotentHint, and nondestructive. The description adds important behavioral context: session names can be null for recent sessions. This goes beyond 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 concise, using a single sentence plus structured XML tags for use case and notes. However, it could be slightly more efficient by integrating the notes into the main text.

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 output schema exists, the description explains the tool's purpose and a key behavioral note (null names). However, it omits parameter descriptions, which are essential for proper invocation. This is a moderate gap.

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%, yet the description does not explain the parameters (limit, offset). It only describes the output, leaving the agent to infer input semantics from the schema alone. This is a significant gap.

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 verb 'auflisten' (list) and the resource 'parlamentarische Sessionen' (parliamentary sessions). The use case explicitly mentions using session IDs for filtering votes or transcripts, distinguishing this tool from siblings like get_votes or get_transcripts.

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 a clear use case for when to use the tool (fetching session IDs for filtering). However, it does not explicitly state when not to use it or mention alternatives, though for a simple listing tool this is 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?

The <important_notes> section discloses non-obvious behavior: the output is capped by max_chars, truncation is signaled by is_excerpt=True, and note/next_offset explain how to load the continuation. It also promises no silent truncation and no summarization, going beyond the readOnly/idempotent 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 well-structured with a lead sentence, a <use_case> block, and an <important_notes> block. Every sentence adds functional value, and the formatting makes it easy to scan.

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-record retrieval tool with rich annotations and an output schema, the description covers what is fetched, when to use it, and the pagination/truncation contract. No return-value documentation is needed because the 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?

With schema description coverage at 0%, the description compensates by tying transcript_id to the lookup key and explaining that max_chars caps the response, with is_excerpt/next_offset for continuation. It does not describe the offset parameter directly, but the continuation note implies its role.

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+resource statement: 'Den vollen Wortlaut eines einzelnen Votums nach Transkript-ID abrufen' (retrieve the full wording of a single speech by transcript ID), which clearly distinguishes this tool from the search-oriented siblings. It also names the exact follow-up use case after parlament_search_transcripts.

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 <use_case> section explicitly says to use this after a search with parlament_search_transcripts to get the complete, quotable wording of a specific Votum. It does not list alternative tools or explicit 'when not to use' exclusions, but the context is clear enough to guide 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 indicate readOnly, idempotent, and non-destructive nature. Description adds value by highlighting the importance of 'meaning_yes'/'meaning_no' for correct interpretation, which is not evident 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?

Description is concise with two sentences plus structured use_case and important_notes. No redundancy, but could be more efficient by integrating note into main text.

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 tool has an output schema, return values need not be explained. However, parameter semantics are missing and usage context is sparse. For a simple retrieval tool, it is incomplete.

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%, meaning parameters lack descriptions in the schema. The tool description does not explain any parameters (limit, offset, keyword, session_id), relying solely on the schema which is insufficient.

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 retrieves parliamentary votes with yes/no meaning, using specific verb 'abrufen' and resource 'Abstimmungen'. Use case examples differentiate from siblings like get_sessions or get_business.

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 explicit guidance on when to use this tool versus alternatives like parlament_search_business or when not to use it. The use case provides context but lacks comparative direction.

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, idempotentHint, and destructiveHint=false. The description adds critical behavioral details beyond annotations: case-sensitive OData substringof search, maximum 100 results per call, and pagination via offset. No contradictions.

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 well-structured with tags for use_case, important_notes, and example. It is concise (around 4 sentences plus tags) and front-loaded with the main purpose. Minor verbosity from tags but overall effective.

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 presence of an output schema, the description adequately covers use cases, important technical notes (case sensitivity, pagination), and provides an example. It is complete enough for a search tool with well-documented 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?

The input schema already has detailed descriptions for each parameter (limit, offset, status, etc.), so the description adds minimal additional semantic value. It mentions OData substringof for title search but does not explain each parameter beyond the schema. Baseline 3 is appropriate given 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 purpose: searching parliamentary business (motions, interpellations, etc.) in German. It distinguishes itself from sibling tools like parlament_get_business (for single business) and other search/get tools for sessions, transcripts, votes, and members.

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 includes a use_case tag with specific political research topics, providing clear context for when to use the tool. It does not explicitly state when not to use it, but the sibling tools are distinct enough to imply 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 already declare readOnlyHint=true and destructiveHint=false, confirming safe read operation. The description adds behavioral detail beyond annotations by specifying the default active_only=True behavior and canton format, though it omits pagination details which are covered by the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with a single sentence, a use case tag, and important notes tag. No wasted words; all content is valuable and 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?

Given the seven parameters and presence of an output schema, the description covers the main purpose, typical use cases, and key behavior. It lacks explanation of offset/limit but those are standard and schema-defined. Overall adequate for a search 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?

The description adds moderate value over the schema: it reinforces canton format and active_only default, but the schema already provides adequate descriptions for all parameters (e.g., party, council, last_name). With 0% overall schema description coverage, the tool description compensates partially but not heavily.

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 searches for members of National and Ständeräte, and distinguishes from siblings by mentioning synergy with parlament_search_business for identifying motion authors. The use case example reinforces the purpose.

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 scenarios (finding all Zurich members or members of a party) and notes important defaults and format requirements (active_only=True, canton as 2-letter code). It also guides users to combine with a sibling tool.

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 mark readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral detail beyond that: it returns only real spoken contributions (not voting lines), explains that the Language filter deduplicates editions but does not hide French/Italian votes, and states coverage starts at 1999-12-06. These are valuable context for the agent.

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 structured with distinct sections (main statement, return format, pointer to related tool, use_case, important_notes, example). Every sentence adds value: the limitation of excerpts, the language filter behavior, coverage start, and a concrete example. It is detailed but not bloated, and the front-loaded purpose sentence is immediately clear.

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 description covers the essential aspects for a search tool: what it searches, what it returns (short quotable extracts with citation and stable URL), what it does not return (full text), which sibling to use next, scope limitations, and coverage date. It also addresses the Language filter nuance. Given the output schema exists and the input schema has detailed per-parameter descriptions, this is fully 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?

While the description does not individually document each parameter, the input schema itself provides thorough descriptions for all nested properties (limit, offset, council, dates, keyword, session_id, speaker_name, business_number). The tool description adds practical usage meaning via the example (speaker_name='Munz', session_id=5202, keyword='Volksschule') and latency guidance for combining parameters, which goes beyond raw schema listings.

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+resource: 'Wörtliche Wortmeldungen aus den Ratsdebatten durchsuchen (Amtliches Bulletin)' – clearly searching verbatim contributions in council debates. It further distinguishes itself from siblings by stating it returns 'kurze, zitierfähige Auszüge (kein Volltext)' and explicitly redirects to parlament_get_transcript for the full text of a single vote.

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 guidance: use this tool for search/snippets, then call parlament_get_transcript for the exact full wording. It also gives a concrete use case and performance tips (combine session_id, business_number, or a date window with a free keyword for best latency), plus notes about synergie with fedlex-mcp.

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