mcp-liveness

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

Annotations only say readOnly/openWorld/non-idempotent; the description goes well beyond that, disclosing that the tool makes a live network call to a third-party endpoint, probes OAuth discovery on 401, distinguishes 402/403/401 semantics, and notes that a non-JSON-RPC 200 counts as unreachable. The `skipCredentialCheck` trade-off (one request vs. up to five, losing credential-obtainability reporting) is exactly the kind of behavioral detail annotations cannot carry.

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 the action, then a compact outcome glossary, then a one-line usage rule. Every sentence carries load — the outcome list substitutes for the absent output schema, and the base-rate sentence justifies the tool's existence.

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, and the description enumerates the full result vocabulary along with what each outcome means, so an agent knows exactly what it will get back. For a two-parameter, read-only diagnostic tool this leaves nothing material unspecified.

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 baseline is 3; the description earns a bump by pinning `name` to "the official MCP registry" and clarifying that credential-obtainability reporting is what `skipCredentialCheck` trades away, which gives the flag a decision-relevant meaning beyond the schema's speed note.

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: make one `initialize` call to the endpoint named in a registry listing and report what a credential-less client receives. The enumerated outcome vocabulary (`usable`, `needs_credential`, `charged`, `unreachable`, `local_only`, `not_listed`) makes the tool's scope unmistakable and distinct from the sibling `mcp_liveness_explain_outcomes`, which evidently only explains those outcomes.

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?

Gives an explicit trigger: "Call this before spending a call on a server you found in the catalogue," backed by a base-rate justification (two in five remote listings fail). No explicit when-not clause or named alternative, but the pre-flight positioning is clear enough to route correctly.

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 cover the safety profile (readOnly, idempotent, closed-world), but the description goes further: it discloses that snapshots hold content hashes not bodies, so schema diffs are not returned directly and `detail` exposes release-asset locations instead, and that a missing month yields an error naming available months rather than a misleading empty diff.

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 purpose, then usage, then caveats, with each paragraph carrying distinct information. It is somewhat long for two parameters, but the added sentences cover hash-vs-body and error semantics that are not filler.

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 tool with no output schema and non-obvious semantics, the description explains the return content (changed tools plus kind of change), the escape hatch for exact diffs, and the failure mode for missing snapshots. An agent has enough to call it and interpret the result correctly.

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 both parameters are already documented, including the `since` omission behavior. The description reinforces 'exact name' and 'the month you name' but adds little syntax or format detail beyond what the schema provides; 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?

States a precise verb and resource: report which tools were added, removed, or changed (description/input schema/output schema) between a named month and the latest snapshot. This is clearly distinguishable from the sibling liveness_check, which the description itself contrasts against.

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?

Gives explicit triggers ('server worked before and is behaving differently now', 'a prompt or integration ... has started failing', 'before trusting a tool description you cached') and explicitly contrasts itself with a liveness check: liveness says it answers today, this says whether it is still the same server.

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?

Adds concrete behavioral facts beyond the annotations: 'Makes no request and costs nothing' tells the agent there is no network I/O or billing impact, which is stronger than readOnlyHint alone. 'Call it once' reinforces the single-shot nature of a pure lookup 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?

Two sentences, front-loaded with the return content and followed by cost/usage guidance. Every clause earns its place with no redundancy.

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?

A zero-parameter, read-only reference tool with no output schema; the description explains both what is returned (six outcomes, meanings, next steps) and the invocation contract (once, free). Nothing an agent needs 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?

The tool takes zero parameters, so per the rubric the baseline is 4; there is nothing param-related left to describe, and the description correctly avoids inventing inputs.

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 ('Return the six outcomes this server can report') plus the payload's structure (meaning for an agent, next steps). It implicitly separates itself from the sibling mcp_liveness_check by positioning itself as the interpreter of that tool's results.

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?

Explicitly says 'call it once to interpret mcp_liveness_check results,' which names both the trigger and the sibling it complements. It stops short of saying when not to call it (e.g., if results are already understood), but the direction is clear.

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