lastseen score

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

With no annotations, the description carries the behavioral burden and does so well: it specifies the return shape (depends_on[], counts, n, provenance), warns that the answer is factual rather than a risk score, and cautions that empty/zero results mean 'no edges on record,' not absence of risk. It omits any auth or rate-limit notes, but for a read-only register lookup that is minor.

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 trigger with a 'When to call' label, then returns, then an example — an efficient, scannable structure. Slightly redundant in restating the id parameter at the end, but every sentence contributes.

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 correctly documents the return fields and their interpretation limits, which is exactly what an agent needs. Combined with the trigger and example, nothing essential for correct invocation is missing.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: it defines the id as an 'MCP schema-server identifier whose dependency edges to inspect' and supplies an example value. It clarifies what is being looked up rather than merely restating the field name.

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+resource ('dependency edges to inspect' for a given MCP schema-server id) and explicitly distinguishes the output from a sibling by saying it returns 'dated facts, not a score,' which sets it apart from trust_score. An agent can identify the tool's function without opening the 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?

Provides an explicit 'When to call' clause tied to a concrete moment (before connecting to or recommending an MCP server) and a condition (you care whether dependencies were dead or dormant). It stops short of naming an alternative tool or stating when-not-to-use, so it is clear context without full routing 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?

With no annotations, the description carries the full behavioral burden. It usefully discloses the return payload and clarifies that results are dated facts rather than a derived score, but says nothing about behavior on an unknown/unobserved server id, how far back history goes, or any access constraints. Adequate but with real gaps for a zero-annotation tool.

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-loaded 'When to call' then 'Returns' then parameter note is a good order and every section is short. The inline Example JSON adds little beyond the schema's own example, keeping it just short of maximal.

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?

There is no output schema, so the description correctly spends its words enumerating the return fields and their meaning. For a single-parameter read tool this is nearly complete; only edge-case behavior (no history for an id) is unaddressed.

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 single required parameter is fully described in the schema, so baseline is 3; the description adds a genuinely new fact by stating the id lives in the same identifier space as trust_score, which matters for cross-tool chaining. The repeated example value is redundant with the schema but the namespace note is real added value.

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 the resource (an MCP server's observed schema/tool-list history) and the shape of what comes back (first_seen, last_observed, drift_events, observations[]), then explicitly distinguishes itself from its two siblings by routing the derived score to trust_score and dependency mortality to dependency_risk. An agent can pick this tool without opening any 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?

The 'When to call' section gives concrete trigger conditions (before integrating, before pinning tool names, when checking whether the tool list changed under the same server id) and the 'Returns' section explicitly hands off to trust_score for the score and dependency_risk for dependency counts. When-to-use and alternatives are both stated rather than inferred.

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, the description carries the full burden and does substantial work: nulls are 'never invented', status takes scored|unresolved|insufficient_data, depth 2 answers mortality more than merit, and the display string must be cited as-is. It omits operational traits such as auth, rate limits, or cost, which keeps 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?

Front-loaded with 'When to call:' and 'Returns:' headers, and most sentences earn their place by constraining interpretation. The trailing id definition largely restates the schema description, which is the one redundant piece.

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?

There is no output schema, so the description must explain the return payload, and it does: fields, null semantics, status enum, depth meaning, weights/resolution, and methodology URL, plus the caveat about what the score does not mean. An agent has everything needed to call it and interpret the result.

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 already 100%, so the baseline is 3, but the description adds genuine disambiguation: the id is an MCP schema-server identifier and explicitly is not an npm package name, Action slug, or Docker image. That prevents a realistic class of wrong invocations.

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 states a specific verb and resource: check the public record on whether an MCP server is still maintained, and returns a scored trust judgment. It does not, however, differentiate itself from the siblings dependency_risk and schema_history, even though its own 'dependency_health' dimension clearly overlaps with dependency_risk.

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 'When to call:' clause gives an explicit triggering moment (before connecting, installing, wiring into an agent, or recommending a server) and boundaries ('not a prediction, not advice, not a ranking of alternatives'). It still never names the sibling tools as alternatives for adjacent questions, so routing between dependency_risk, schema_history and this tool is left to inference.

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