ADITUS Developer Portal MCP

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

Annotations already declare read-only, idempotent, and non-destructive behavior, and the description adds substantial non-obvious details: large response bodies are truncated, leading '/api' or '/v1' prefixes are ignored, path parameter spellings are flexible, and query strings select among duplicate recordings with an `{ ambiguous: true, candidates: [...] }` fallback. No contradiction with 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 core purpose and accepted input form are front-loaded, and each subsequent sentence covers a necessary edge case: path flexibility, prefix stripping, duplicate recordings, ambiguity handling, and no-match behavior. The description is dense but every clause earns its place.

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 still specifies what the response contains, mentions truncation and where full text lives, gives the exact ambiguity payload shape, and describes the no-match error behavior. The agent has enough information to call and interpret 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 schema documents the single `endpoint` parameter with examples, but the description adds decisive parsing semantics: it accepts either an id or 'METHOD /path', tolerates any path-parameter spelling, ignores leading API prefixes, and explains how a query string disambiguates duplicate recordings. This is far beyond what the schema alone 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 opens with 'Full contract of one endpoint' and enumerates the exact contents (method, URL, auth, query/header params, request body example, example responses), so the agent knows precisely what operation is performed. It is clearly distinct from search/list tools: it takes an endpoint id or 'METHOD /path' and returns the detailed contract.

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 tells the agent where the input comes from ('endpoint id from search/list'), how to resolve duplicate recordings, and what to do on ambiguity ('call again with one of the candidate ids'). It does not explicitly name sibling tools or state when not to use this tool, so it falls just short of fully explicit alternative 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 already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: the payload is Markdown, and supplying a section returns only a slice of the document rather than the whole guide. No mention of size limits or truncation, but the bar is lower with annotations present.

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?

Front-loads the return format ('Markdown of an integration guide') before the catalogue, and the final sentence covers the optional narrowing parameter. Dense but each clause carries distinct information; the long middle enumeration is justified by the four guide families it disambiguates.

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?

No output schema exists, so the description carries the burden of describing return values, and it does so (Markdown, full guide or single section). With 100% schema coverage and read-only annotations, the definition leaves no blocking gap for correct invocation.

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 genuinely adds meaning the schema does not: it explains what each guide id actually contains and clarifies that 'section' accepts a heading or slug. This is additive rather than restating the schema's example list.

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 clearly that it returns Markdown content for an integration guide and then catalogues the distinct guide families, so an agent knows exactly what resource is fetched. It distinguishes among the guide variants (compact contract vs. full docs vs. non-technical overview), though it never names or contrasts the sibling tools (search_docs, list_modules, get_endpoint).

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 catalogue implies when each guide id is appropriate, and the closing sentence explains that passing a section heading narrows the fetch. There is no explicit guidance on when to prefer this over search_docs (e.g., when the guide id is unknown) or any exclusion, so usage is only implied.

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, closed-world, non-destructive, so the safety profile is covered. The description adds value beyond that by enumerating the returned fields, which matters because there is no output schema. It omits pagination/volume behavior, keeping it short of a 5.

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 compact sentence covering scope and return shape, followed by a short routing directive. Front-loaded, no filler, every clause earns its place.

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 read tool with no output schema, the description plus annotations cover what the agent needs: what it lists, what comes back, and where the id comes from. Only the absence of any note on result size or pagination leaves a small 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 100% and the schema itself gives the meaning and an example ('ticket-purchase-registration'), so the baseline of 3 applies. The description adds only the source of the id (list_modules), a minor supplement rather than new 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 (list) and resource (endpoints) scoped to 'one module', and enumerates the returned fields (id, method, path, sub-group, summary). This distinguishes it cleanly from list_modules and the singular get_endpoint without opening either schema.

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 an explicit prerequisite and provenance for the argument: 'Use the module id from list_modules.' That is real routing guidance. It stops short of stating when to prefer this over get_endpoint or search_docs, so it is clear context rather than full when/when-not 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 already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds genuine domain context beyond that, explaining the semantics of the 'direction' field (inbound vs outbound) and mentioning that documentation URLs and integration guides are included.

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 delivers the core content, with the module fields listed first and the integration-guide addendum second. It is efficient, though the parenthetical definition of direction makes it slightly long for one 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?

With no output schema and no parameters, the description carries the burden of explaining the return shape and does so adequately: modules with direction, endpoint counts, doc URLs, plus integration guides. It is complete enough to call correctly, missing only explicit sibling routing.

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 nothing for the description to disambiguate; the baseline of 4 applies. No parameter information is expected or missing.

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 verb+resource ('All top-level ADITUS API modules') and enumerates the returned fields (direction, endpoint counts, documentation URLs, integration guides). It is clear what the tool does, but it does not explicitly differentiate itself from siblings like list_endpoints or get_endpoint.

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 as a discovery/entry-point call ('top-level modules', 'also lists the integration guides'), but there is no explicit when-to-use or when-not-to-use guidance, and no alternative sibling is named for the cases where the agent should instead drill into endpoints or guides.

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, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the language-normalization layer with a concrete example ('aussteller' → exhibitor), the corpus boundaries, and the fact that results are ranked and carry reusable ids.

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, front-loaded with what is searched before the language behavior and the return-value note. The long parenthetical enumerating the guides is dense but each clause carries real information; no sentence is 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?

With no output schema, the description carries the return-value burden and discharges it ('ranked hits with ids usable in get_endpoint / get_guide'). Combined with the searchable-corpus definition and the bilingual query behavior, an agent has everything needed to call this 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?

Schema description coverage is 100% — both query and limit are documented with examples and constraints in the schema itself. The description's language note reinforces the schema's bilingual examples but adds no syntax, format, or defaulting detail beyond it, 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 precise verb (full-text search) and enumerates the searchable corpus: API modules, endpoint name/path/description, and named guides. This clearly distinguishes it from the retrieval-by-id siblings get_endpoint and get_guide, and from the listing 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 closing sentence routes the agent forward — 'Returns ranked hits with ids usable in get_endpoint / get_guide' — which establishes the intended search-then-fetch workflow. It also tells the agent non-English (German) queries are valid, but never states when to prefer search over list_endpoints/list_modules.

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