lastseen score

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It clearly states this is a read-only factual query ('Facts, not a score') and specifies what data is returned (dead/dormant counts), avoiding any misleading claims. No annotation contradiction exists since annotations are absent.

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 two concise sentences that efficiently convey purpose, output, and tone. Every phrase adds value, with no redundancy or filler. Front-loaded with the core function.

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 (1 parameter, no nested objects, no output schema), the description is largely complete. It explains the return type (dead/dormant counts) and the factual nature. Could benefit from mentioning the output format (e.g., JSON structure), but not critical for a simple lookup 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% with one well-documented parameter ('id' with format example). The description adds minimal meaning beyond the schema (e.g., the context of 'from the register'), but the schema already clearly explains the parameter. A baseline 3 is appropriate.

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 an MCP server's dependencies and their mortality state (dead/dormant counts), distinguishing it as a factual data retrieval tool rather than a scoring tool like trust_score. It uses specific verbs ('dependencies and their mortality state') and explicitly differentiates itself from trust_score.

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 implies usage for inspecting dependency health, but provides no explicit guidance on when to use it versus siblings (schema_history, trust_score) or when not to use it. The phrase 'Facts, not a score' hints at contrast with trust_score, but lacks direct alternatives or conditions.

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?

No annotations are provided, so the description carries the full burden. It discloses the tool is read-only and factual ('Facts from the register') and returns time-series data, but omits details like permissions, error behavior, or what happens for unknown 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?

The description is a single sentence with a clarifying fragment, no wasted words, and the key action and result are front-loaded. However, the phrase 'a series when known' is slightly vague, preventing 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?

In the absence of an output schema, the description lists the return fields (first_seen, last_observed, drift events) which is helpful. However, it doesn't specify the data structure (e.g., array or object) or define 'drift events', leaving some ambiguity.

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 context that the 'id' parameter refers to an MCP server identifier, supplementing the schema's example. With 100% schema coverage, baseline is 3; the description provides minimal extra meaning beyond that.

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 returns dated observations (first_seen, last_observed, drift events) for an MCP server, which distinguishes it from sibling 'trust_score' by explicitly saying 'not a score'. However, it does not fully distinguish from 'dependency_risk', leaving some ambiguity.

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 guidance on when to use this tool versus siblings 'dependency_risk' or 'trust_score'. The description only explains what it does, not the appropriate context or exclusions.

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 bears full responsibility for behavioral disclosure. It explains the score's nature (derived, not predictive/advice), the depth aspect, and the output format via examples. The methodology link adds further transparency. However, it does not mention if the tool makes network calls, has rate limits, or requires authentication, though these are likely implicit for a read-only score retrieval.

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 reasonably concise and front-loaded with the core purpose. Every sentence adds value, including the depth explanation, disclaimer, and methodology link. It is slightly verbose with the example, but this aids understanding. Could be trimmed slightly without loss.

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 absence of an output schema, the description adequately explains the return value through the 'display' example and the notion of depth. It provides enough context for an agent to interpret the result. However, the exact JSON structure of the response is not specified (e.g., whether the display is a string or part of a larger object), leaving minor ambiguity.

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% for the single required parameter 'id', which includes a clear example (io.github.owner/name). The tool description adds no additional semantic value beyond what the schema provides. The baseline score of 3 is appropriate since the schema does the required work.

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 it provides a 'Derived trust score (0-100) for an MCP server', specifying the source (lastseen.dev register) and computational method. It distinguishes itself from siblings (dependency_risk, schema_history) by focusing on trustworthiness rather than risk or history. The purpose is unambiguous and specific.

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 offers no guidance on when to use this tool versus sibling tools like dependency_risk or schema_history. It does not mention when the tool is appropriate, when it is not, or any prerequisites. The agent must infer usage solely from the tool name and description, which is insufficient given related alternatives exist.

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