Stimulsoft Documentation MCP Server

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the return format ('JSON array of { id, name, description } objects'), explains the relationship to sti_search ('returned platform `id` values are the exact strings accepted by the `platform` parameter of `sti_search`'), and provides performance/cost context ('cheap (no OpenAI call, no vector search)'). It doesn't mention error conditions or rate limits, but provides substantial behavioral 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?

The description is efficiently structured with three focused paragraphs: (1) what the tool does and returns, (2) when to use it and its relationship to sti_search, (3) performance characteristics and usage encouragement. Every sentence adds value with zero redundancy or filler content.

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 zero-parameter tool with no annotations and no output schema, the description provides comprehensive context: clear purpose, explicit usage guidelines, detailed behavioral information including return format and tool relationships, and performance characteristics. It fully compensates for the lack of structured metadata.

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 tool has 0 parameters with 100% schema description coverage. The description appropriately doesn't waste space discussing non-existent parameters. It does mention the relationship between this tool's output and sti_search's parameters, which adds valuable semantic context about how the tools interact.

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 explicitly states 'List every Stimulsoft product/platform that has indexed documentation available through this MCP server' - a specific verb (List) + resource (Stimulsoft product/platform) combination. It distinguishes from the sibling tool sti_search by explaining this tool provides platform metadata while sti_search performs searches within those platforms.

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 on when to use this tool: 'CALL THIS FIRST when the user's question is ambiguous about which Stimulsoft platform they are using, or when you need to pick a valid `platform` value to pass into `sti_search`.' It also mentions an alternative (sti_search) and includes cost considerations ('This tool is cheap... call it freely whenever you are unsure').

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 full burden and delivers rich behavioral context. It explains the search is 'powered by OpenAI embeddings + cosine similarity', handles 'queries in any language', advises on search strategy (e.g., reformulating queries if low scores, preferring multiple focused searches), and emphasizes critical constraints like 'Your training data is almost certainly out of date' and the mandate to 'MUST call this tool rather than rely on memory'.

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 clear sections (overview, usage guidelines, search strategy, exclusions, important notes) and uses bullet points for readability. While lengthy, every sentence adds value—no redundant information. It could be slightly more concise but remains highly efficient given the complexity of the tool.

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's complexity (semantic search over extensive documentation), no annotations, and no output schema, the description provides comprehensive context. It details the return format ('ranked JSON array of matching sections' with fields like platform, category, content, score), explains cross-lingual handling, offers practical search strategies, and sets clear boundaries for usage. This fully compensates for the lack of structured metadata.

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 baseline is 3. The description adds meaningful context beyond the schema: it explains that queries should be passed 'almost verbatim' without translation, provides specific examples of good vs. bad queries, and offers strategic advice on when to use 'platform' parameter (e.g., 'If the target platform is obvious from context') and how to handle uncertainty (call sibling tool or omit). This elevates the score above baseline.

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 explicitly states the tool performs 'authoritative semantic search over the official Stimulsoft Reports & Dashboards developer documentation' and specifies it returns 'a ranked JSON array of matching sections' with detailed structure. It clearly distinguishes from its sibling 'sti_get_platforms' by being the search tool versus a platform-listing tool.

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 extensive explicit guidance on when to use this tool with bulleted examples (e.g., 'how to do something in Stimulsoft', rendering/exporting, connecting to data, embedding components, errors/licensing, etc.) and when NOT to use it ('general reporting theory unrelated to Stimulsoft, non-Stimulsoft libraries, or pure programming questions'). It also references the sibling tool 'sti_get_platforms' for platform identification.

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