SRI — MCP Server Inspector

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

Beyond the readOnlyHint=true annotation, the description discloses several important behavioral traits: it is free and requires no key, it reads the published source of servers from a corpus of 2,781 entries, it reports observations rather than a safety verdict, and an empty result means 'nothing found in categories checked', not safety. It also notes that l402_token is deprecated and ignored, and that payment, when charged, happens over x402. This is rich, candid behavioral context that goes well beyond the structured annotation field.

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 appropriately compact for a security-relevant tool, with each sentence adding a distinct piece of value: the free no-key nature, the file:line anchors, the call-before-connecting guidance, the kinds of findings, the negative use-case, the observation-versus-verdict caveat, and the corpus scope. It is front-loaded with the most decision-relevant fact (what the tool does and that it is free/private). 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?

Given that the tool has an output schema, an annotations block, and 100% schema coverage, the description still adds essential context: when to call it, what not to call it for, the meaning of an empty result, the corpus size and coverage index, and the x402 payment nuance. An agent has everything needed to select, invoke, and interpret this tool correctly without hunting elsewhere.

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 schema already documents all four parameters. The description adds extra meaning by clarifying that 'name' can be either a registry name or a package name for unregistered reference servers, and by stating that 'ecosystem' always defaults to 'mcp' and that l402_token is deprecated/ignored. These additions go beyond the raw schema descriptions and help an agent form correct inputs, though the schema already carries most of the semantic weight.

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 precise verb and resource: it reads the published source of an MCP server and reports observations anchored to file:line with quoted code. This goes beyond a generic 'check' by stating exactly what is returned and how, and it clearly differentiates from the sibling get_corpus_coverage, which is about corpus coverage rather than single-server analysis.

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 an explicit condition for use ('Call this before connecting to, installing, or invoking an MCP server you have not read yourself') and an explicit exclusion ('Do NOT call this for ordinary npm or PyPI libraries'). It also names the sibling tool indirectly by pointing to corpus coverage as a separate concern, so the agent knows when this tool is and isn't appropriate.

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 include readOnlyHint: true, but the description adds significant transparency beyond that: 'No arguments', 'Returns how many... and the share of them with each category', and explicitly states limitations: 'aggregate counts only - no per-server findings, and no verdict about any individual server.' This fully clarifies behavioral scope.

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—two sentences. The first sentence states the function, and the second gives usage context and limitations. No filler or redundant phrases. It is front-loaded with the key information and every sentence adds value.

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 simplicity (no params, simple aggregate output), the description fully covers what it does, how to use it, and what it doesn't do. The existence of an output schema covers the return format, so the description doesn't need to detail that. It is complete and actionable.

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, and the schema is empty with 100% coverage. The description even states 'No arguments', which aligns with the schema. Since there are no parameters to explain, a baseline of 4 is appropriate; the description doesn't need to add param 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?

The description clearly states the tool's function: 'Returns how many MCP servers have been read at source level, and the share of them with each category of finding.' It also differentiates from the sibling tool by explicitly noting it provides only aggregate counts with 'no per-server findings', making its purpose distinct.

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 explicit guidance: 'Use this to judge whether checking a specific server is worth it before you look one up.' It also implicitly contrasts with the sibling tool by stating it does not give per-server details, which orients the agent on when to use this vs. check_mcp_server.

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