Japan JGB Yields MCP

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

No annotations, so the description carries the burden; it does disclose that the call is free and identifies the upstream source, which helps with provenance and cost concerns. It does not say how fresh the 'latest' data is, whether it is cached, or what the response shape looks like.

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 short sentence with the resource and scope front-loaded; nothing is wasted, though the leading 'FREE.' fragment is stylistically odd and marginally less informative than the rest.

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 simple zero-param fetch with no output schema, the description should at least sketch the return (a yield curve by tenor) — it implies the 1y–40y range but doesn't state format, units, or update cadence. Adequate but with clear gaps.

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 the schema provides nothing for the description to compensate for and the baseline of 4 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?

Specific verb+resource: 'latest JGB reference yields', with maturity scope (1y–40y) and a named source (MoF Japan). It does not explicitly distinguish itself from siblings 'recent' or 'tenor', so it falls short of a 5.

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 statement of when to use this versus 'recent' or 'tenor', and no prerequisites or exclusions. 'Latest' implies a snapshot use case, but that is inference rather than 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?

No annotations exist, so the description carries the full burden; it does disclose the return cardinality (~10), ordering ('last'), and a paid/subscriber access gate. It omits what happens when no access_token is supplied (the schema marks it optional), error behavior, and the shape of returned observations.

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 terse fragments with no waste, but 'PRO.' is front-loaded ambiguity rather than purpose, and 'JGB' is left unexpanded, making the statement cryptic for an agent without domain knowledge.

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 simple one-parameter read tool the description is minimally survivable, but with no output schema it says nothing about the returned fields (dates, tenors, yields) and leaves the duplication with 'latest_yields' entirely unresolved.

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?

Only one parameter and schema description coverage is 100%, so the schema already explains access_token fully. The description adds nothing about it beyond the redundant 'PRO' signal, which is the baseline case for full schema coverage.

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 (JGB yield observations) and its scope (the ~10 most recent), which is more than the opaque tool name 'recent'. But it never distinguishes this from the near-identical sibling 'latest_yields', so an agent cannot tell from the text which one to call.

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 use this versus 'latest_yields' or 'tenor', despite 'latest_yields' sounding like a direct substitute. The 'PRO' prefix implies a paid tier but is not explained as a usage prerequisite.

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 hints at a paid/pro subscription ('PRO.') and the schema has an access_token, but it never states auth requirements, what happens without a subscriber token, response shape, or freshness semantics of 'latest'.

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 short sentence with the key enumeration front-loaded; little waste. The cryptic 'PRO.' prefix is the only real inefficiency.

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 and no annotations on a two-parameter tool requiring a subscriber token, the description should explain return format, auth/failure behavior, and freshness of 'latest'. None of that is present, so an agent cannot confidently invoke it.

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 50% (access_token documented, 'years' undocumented). The description usefully enumerates the valid tenor years (1-40), compensating somewhat for the bare number type, though it doesn't clarify the singular 'years' vs 'one tenor year' mismatch or the token's fallback behavior.

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 it returns the latest yield for a single tenor year, which is a recognizable verb+resource. However, it does not distinguish itself from the sibling latest_yields (likely all tenors) or 'recent', leaving scope differentiation to inference. The 'PRO.' prefix is opaque about what it means for purpose.

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 explicit when-to-use, no exclusions, and no alternatives named despite the presence of latest_yields and recent siblings. An agent must guess whether this or latest_yields is appropriate for a single-tenor lookup.

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