縦綱 Tatezuna — o-sumo

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

The annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the useful default behavior (omitting monthKey returns the latest basho) and the division scope, but says nothing about the shape of the returned rankings or how errors surface for an invalid monthKey.

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 compact sentences with the core purpose front-loaded and the optional-parameter behavior second. Nothing is wasted, though the parenthetical example duplicates the schema.

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?

This is a simple, single-parameter, read-only lookup with fully documented schema and no output schema to explain. The description covers purpose, default behavior, and historical lookup, which is sufficient for correct invocation.

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 the schema already documents monthKey's YYYYMM format and its default to the current basho. The description repeats the format and example ("202609") without adding new meaning such as valid ranges or how out-of-range keys behave; 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 names a specific verb and resource ("Get official Grand Sumo banzuke") and narrows the scope to "rankings for makuuchi and juryo divisions", so an agent knows exactly what data it returns. It does not explicitly distinguish itself from the nearest sibling, list_basho, which is thematically adjacent.

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?

It clearly states the parameterized usage pattern: pass monthKey for a historical basho, omit it for the latest one. There is no guidance on when to prefer this tool over siblings such as list_basho or get_torikumi, and no exclusions or prerequisites are given.

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?

The annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description contributes the return content (profile plus career record), but says nothing about behavior on invalid or unknown IDs, which is the main remaining unknown for this call.

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 front-loaded sentence with the resource and the key constraint; nothing is padded or restated.

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 read-only, one-parameter lookup with no output schema, the definition covers what the tool does and roughly what it returns. The only real gap is error behavior for a nonexistent ID, which is minor at this complexity.

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?

With one parameter and 100% schema coverage, the schema already documents "Official rikishi ID (e.g. 4227)". The description only echoes "numeric ID", adding no format, range, or validity guidance beyond the structured field, so baseline 3 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?

The description names a specific verb+resource pair ("Get detailed profile and career record for a specific rikishi") and constrains the lookup key to a numeric ID, which clearly separates it from list_basho and get_banzuke. It never names or contrasts with search_rikishi, the closest sibling, so the differentiation is implied rather than stated.

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?

"By numeric ID" quietly implies you must already know the ID, which hints that search_rikishi is the discovery path, but the description never says so or gives any when-not condition. An agent must infer the workflow rather than read it.

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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds only the day-scoping notion; it does not mention what a bout record contains or how result vs schedule differ in practice. Adequate but not rich beyond structured fields.

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 compact sentence with the resource and date format front-loaded, no wasted clauses. The parenthetical format note mildly duplicates the schema but is harmless.

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 two-parameter read tool with a full schema and safety annotations, this is close to sufficient. However, with no output schema, the description does not hint at the shape of returned bout data, leaving an agent to guess what it gets back.

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 both the mode enum and pathDate pattern documented in the schema. The description restates the YYYYMMDD format and alludes to result/schedule without adding new meaning, so the baseline of 3 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?

The description gives a specific verb (Get) and resource (torikumi) and clarifies it returns either match results or a schedule for a given day, which separates it from ranking (get_banzuke) and profile siblings. It stops short of explicitly naming those siblings as alternatives.

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?

Usage is only implied: fetch torikumi data for a specific day. There is no explicit statement of when to prefer this over get_banzuke or list_basho, and no prerequisites or exclusions are given.

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 declare readOnlyHint=true and openWorldHint=false, so the safety and scope profile is covered. The description contributes real value beyond that by disclosing the result contents (page URLs and API endpoints) and that archived as well as current basho are included, but it does not mention ordering, completeness, or pagination behavior.

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 front-loaded sentence that adds no filler. The phrase 'available in o-sumo' is mildly redundant with the surrounding domain but usefully ties the tool to its data source.

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 zero-parameter read-only list with no output schema, the description is nearly sufficient: it names the scope (current and archived) and the returned fields. It could go one step further by noting whether the returned entries include the identifiers other sumo tools consume.

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 baseline is 4. The description correctly implies no filtering or scoping options are available, leaving nothing for the schema to explain.

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 gives a specific verb ('List') and resource ('current and archived Grand Sumo basho available in o-sumo') and even states what each entry carries (page URLs and API endpoints). The resource is clearly distinct from the siblings (banzuke, rikishi profiles, torikumi), though it never names them explicitly.

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 guidance, no mention that this is the natural entry point for discovering the basho identifiers the other sumo tools likely require, and no stated exclusions. The usage is only implied by the listing nature of the tool.

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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral detail beyond them: a hard cap of 20 results and the exact fields returned (ID, name, reading, current rank, profile URLs). It stops short of disclosing match semantics (exact vs. partial/substring matching), which is the main unknown for a search 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, no filler, and the search scope plus accepted inputs are front-loaded before the return-value clause. Every clause carries information an agent can act on.

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 single-required-parameter, read-only search tool with no output schema, the definition covers input domain, result cap, and returned fields, which is enough to call it correctly. The remaining gaps are matching behavior and what happens when no rikishi match.

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%, and the query parameter's schema entry already states it accepts name or reading with concrete examples ("大の里", "おおのさと"). The description restates the same fact rather than adding meaning, so the baseline 3 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?

The description opens with a specific verb and resource ("Search Grand Sumo rikishi") and names the two accepted key types (四股名 shikona / 読み yomi). It also enumerates returned fields, which implicitly separates it from get_rikishi_profile, but it never names that sibling, so the differentiation is left to inference.

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?

Only implied usage: you search to obtain an ID and profile URLs, which suggests a lookup-then-fetch workflow with get_rikishi_profile. There is no explicit when-to-use statement, no guidance for zero results, and no mention of when get_banzuke or get_rikishi_profile should be preferred instead.

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