Radu Stoian MCP Server

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing that answers are grounded in the site's knowledge base and supplemented with external investigation links, but it omits answer format, latency, and behavior on unanswerable questions. The 'external investigation links' phrasing sits slightly awkwardly against openWorldHint=false, though it appears to describe link content rather than live external calls, so no contradiction is flagged.

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 the core verb and subject up front, followed by the retrieval mechanism. Mildly padded by 'dynamic retrieval engine that grounds its answers by pulling from', but no sentence is wasted.

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 must hint at what comes back; it only says answers are grounded in the knowledge base plus external links, without describing answer shape, citation behavior, or failure output. Annotations and a fully documented schema carry the rest, so this is adequate but 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 100%: both 'query' (with three example questions) and the 'question' alias are fully documented in the schema. The description adds no guidance on phrasing, scope limits, or when the alias should be preferred, so the 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?

The description names a specific verb ('Answers ... questions') and resource ('about Radu Stoian'), and explains the retrieval mechanism that produces the answer. It is clearly distinct from get-investigation-links, get-section, and server-info, though it never explicitly routes the agent away from those siblings even though it mentions the 'external investigation links' they expose.

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 phrase 'generic or specific questions' implies this is the natural-language Q&A entry point, so usage is inferable rather than stated. There is no explicit when-to-use versus get-section or get-investigation-links, and no statement about what to do when the knowledge base cannot answer.

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 covered structurally. The description adds that the payload is a curated static set of external links/profiles, but says nothing about return format (URLs? names? labels?) or whether the set is complete or evolving.

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 front-loaded sentence with no waste; the enumerated sources do useful work. Slightly awkward framing ("for AI agents to investigate") keeps it from a 5.

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, no-output-schema tool, the description largely carries the return-value burden by naming the sources returned. It falls short only on format/shape of the returned data, which the absent output schema leaves unexplained.

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?

Zero parameters, so per the rubric the baseline is 4; there are no parameter semantics to explain and the description correctly implies a no-argument call.

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 ("Returns") and resource ("external links and public profiles") and even enumerates the sources (LinkedIn, GitHub, Substack, etc.). It's clear what an agent gets back, though no sibling is named or contrasted (siblings ask/get-section/server-info don't overlap much, so differentiation is less critical).

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 phrase "for AI agents to investigate Radu Stoian" implies the context in which to call it, but there is no explicit when-to-use, when-not-to-use, or alternative routing. Usage is only inferable from the purpose statement.

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 a closed-world scope, so the safety profile is covered. The description's useful addition is that it returns the *complete text* of a section — relevant since there is no output schema — but it says nothing about behavior on invalid/ambiguous section names or how partial matches resolve.

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?

It is a single front-loaded sentence with the core claim up front, which is good. However, the long parenthetical enumeration of six section names is redundant with the parameter schema and dilutes the one sentence it has.

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 usefully states that the full section text is returned, and the schema enumerates valid section identifiers, so an agent can call it correctly. The remaining hole is error/fallback behavior for unknown sections, which is minor for a simple read 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?

Schema description coverage is 100% and the parameter description already enumerates the canonical sections plus common aliases. The description's parenthetical list of section names largely duplicates that, so it adds no syntax, matching, or fallback semantics beyond the schema. Baseline 3 is warranted.

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 ('Returns the complete text of a specific section from the site's knowledge base'), which is unambiguous about what the tool does. It does not differentiate itself from siblings like 'ask' or 'get-investigation-links', which is the only gap.

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 only implied: an agent can infer it should call this to fetch a known section by name. There is no statement of when to prefer this over 'ask' (e.g. free-form questions) or over 'get-investigation-links', and no guidance on what happens with an unrecognized section name.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds useful context about what the payload contains (runtime environment, knowledge capabilities), but it does not describe the return shape or whether the output is static across calls.

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 lists the content categories without filler. The running enumeration is slightly dense but every clause names a real payload section.

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 must carry the burden of explaining what comes back; it names the categories but not their structure or format, so an agent knows roughly what to expect but not how to consume it. For a no-parameter, read-only info tool this is adequate but not 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. The baseline for a parameterless tool 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 specific verb ("Returns") and resource ("information about this MCP server") and enumerates the content categories: creator details, runtime environment, instructions, and knowledge capabilities. It is clearly distinct from siblings like ask, get-investigation-links, and get-section, though it never explicitly names those siblings as alternatives.

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?

There is no guidance on when to call this tool versus the sibling tools, nor any stated prerequisites or exclusions. The agent can infer it is a discovery/metadata call, but nothing in the text confirms that.

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