renkeimap-info

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

With readOnlyHint already covering safety, the description adds real behavioral value: it is a single-round-trip aggregation of three tools, returns 'same shapes as the single tools', and imposes a mandatory obligation ('★Always relay the included disclaimer and citation★') that no annotation conveys. That obligation is exactly the kind of non-obvious behavior worth surfacing.

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?

Three compact sentences, front-loaded with the composition formula, then inputs, then the mandatory relay warning. The ★ markers are slightly noisy but the content is dense with no 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 composite read tool with no output schema, the description covers what it aggregates, that return shapes match the single tools, and the disclaimer/citation obligation. An agent has enough to call and relay it 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%, and the description's 'Give a slug or the system name as the user wrote it' restates what the schema already documents (slug preferred; query when slug unknown). Baseline 3 is appropriate since the schema carries the parameter meaning.

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 defines the tool operationally as a composite ('One round trip = renkeimap_find_system + renkeimap_status + renkeimap_hintpack'), which tells an agent exactly what it returns and names the three sibling tools it bundles. It could state the verb+resource more directly (identify a system and return its status plus remediation), but the composition formula is unambiguous.

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?

'Use first in support conversations' gives explicit context, and the composition line implies it substitutes for the three single tools. It stops short of explicit exclusions (e.g., when to prefer the individual tools), but the when-to-use signal is clear.

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 readOnlyHint/destructiveHint already covering the safety profile, the description adds real substance: the exact composition of each output cell (tags, one-line lead, source URL, survey date, optional ◎○△× marks from a declared rule file) and the explicit constraint that no ranking or score is produced. It stops short of describing error behavior for unpublished slugs or an invalid count.

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?

Three dense sentences, front-loaded with the core operation and then the output shape, with no padding. Minor deduction for 'Same generator as /compare', which references an external path the agent cannot resolve and adds little selectable value.

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 takes on the burden of describing the return shape, and it does so concretely (per-cell contents, optional marks). Remaining gap is failure handling for unpublished or invalid slugs, which matters for a lookup-by-identifier tool, but overall it is complete enough to call 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 coverage is 100% and the single 'slugs' parameter already carries type, minItems/maxItems and an example, so the schema does the heavy lifting. The description's '2-5 published' adds the 'published' qualifier (a genuine constraint not in the schema), but the 2-5 range merely repeats minItems/maxItems. 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 specific verb+resource ('side-by-side comparison of 2-5 published systems/tools') and even enumerates the compared dimensions (API, contract, price, rate limit, etc.), which is far more than a restated title. It does not, however, distinguish itself from the sibling 'renkeimap_pair', which an agent could reasonably read as the pairwise variant of the same operation.

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 implied: use it when you want N systems lined up on identical fields, and 'No ranking, no score' implies it is not an evaluation tool. But there is no explicit when-to-use statement, no prerequisite (e.g. systems must be published/indexed), and no named alternative such as renkeimap_pair or renkeimap_find_system for finding slugs first.

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/destructiveHint=false, and the description adds real value beyond them: it discloses provenance discipline ('with source and date', 'never a URL found by search') and that no keys or values are returned. It does not cover output shape or pagination for the 'full' mode, so it falls just short of the top band.

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?

Dense but front-loaded: the core behavior leads, followed by a numbered route ranking and the detail note. Every clause carries information (ranking, provenance, read-only), though the parenthetical heavy style is slightly compacted.

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 appropriately explains what comes back (ranked routes with source/date; procedure and evidence in full mode). Combined with 100% param coverage and read-only annotations, an agent has enough to invoke it correctly, though the exact response structure remains only lightly sketched.

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 baseline is 3. The description mostly restates the schema semantics (slug from renkeimap_find_system or a pair suite id; detail='full' adds procedure and evidence) rather than adding new syntax or format guidance.

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: it returns routes INTO one system, ordered by stability, and enumerates the three route tiers (official MCP server, API key/OAuth, file/screen). It explicitly names sibling renkeimap_pair as the route for the file/screen tier, so an agent can place it relative to siblings without opening another 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 stability ordering (most stable first) and the 'never a URL found by search' rule give clear context for when this is the right call when trying to connect into a system. It stops short of explicit when-not-to-use or exclusion conditions versus other siblings, but the context is unambiguous.

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 destructiveHint=false, so the safety profile is covered. The description adds two useful facts: results are restricted to 'published' items and capped at '≤10 each'. It does not, however, explain pagination, what happens when no match is found, or the exact meaning of 'each'.

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 terse sentence that leads with the search verb, which is good front-loading. However the '/compare marks' fragment and '≤10 each' are compressed to the point of ambiguity, trading clarity for brevity.

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 two-parameter, no-output-schema, read-only discovery tool the description covers scope, filterable fields, and a result cap, which is a reasonable minimum. It falls short on distinguishing this tool from the many sibling lookup tools and on clarifying the has filter's practical effect.

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% (query documented, has not). The description partially compensates by explaining that has= keeps items flagged positively in /compare, and by listing the queryable fields, but the seven enum values themselves are left to the schema and the has semantics remain vague.

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 clear verb (Search) over specific resources (published systems, tools, guides) and enumerates the match fields (name / vendor / category / kind word). It does not, however, clearly separate itself from siblings like renkeimap_system_facts or renkeimap_brief, leaving some ambiguity about when this discovery tool is preferred.

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 only usage signal is the cryptic phrase 'has= keeps those /compare marks positive', which implies filtering on comparison-positive items but never spells out when to use this tool versus renkeimap_compare or renkeimap_system_facts. No explicit when/when-not guidance 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?

Annotations already mark the operation read-only and non-destructive, and the description adds meaningful behavioral context: the data is static, sourced from public vendor pages, entries carry sources, and no user data is involved. This goes beyond the annotation baseline and helps the agent understand reliability and privacy expectations.

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 compact and front-loaded: it opens with the tool's content scope, then adds sourcing, privacy, and citation notes. Every sentence contributes useful information without repetition or padding.

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 static lookup, the description covers what results contain, their source, the lack of user data, and the need to cite. With no output schema, it could add a bit more about the response shape, but the stated content types and 'entries' references are sufficient for an agent to select and 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 description coverage is 100% for the single slug parameter, including an example ('kintone'), so the parameter semantics are already fully documented. The description does not add param-specific detail, but no further clarification is needed at this complexity level.

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 title ('エラー文の対処を返す') and description both specify that the tool returns the meaning/handling for vendor error messages for a single system, along with support URLs and login method shape. The 'one system' scope plus the concrete content list clearly distinguishes it from siblings like renkeimap_compare or renkeimap_status.

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 does not state when to prefer this tool over its siblings, nor does it name alternatives. It only implies usage through 'static public knowledge for one system' and adds 'no user data,' but there is no explicit routing or when-not-to-use 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?

Beyond the read-only/destructive annotations, the description adds meaningful behavioral context: results are measured from public primary sources, unmeasured pairs are explicitly reported as such rather than guessed, and the included citation line must be cited when used. These details are non-obvious and useful for trusting and attributing outputs.

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 compact yet information-dense: three sentences cover purpose, output style, data provenance, honesty guarantees, and attribution requirements. It is front-loaded with the core purpose and contains no filler or redundant restatement of the title.

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 two simple slug parameters Wang and annotations confirming safe read-only behavior, the description covers the essential context well. It explains what the tool returns, adds caveats about unmeasured pairs, and includes the citation requirement. It does not spell out exact output serialization, but for this low-complexity tool that is not a critical gap.

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 input schema fully documents both parameters ('a' and 'b' as system slugs), so the description does not need to repeat their meaning. The description only refers to 'two systems' generically and adds no additional syntax, constraints, or examples beyond what the schema already provides. Baseline 3 is appropriate given 100% 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 clearly states the tool's function: it determines whether and how two systems can exchange data, with per-method verdicts and field-name overlap. The title reinforces this by saying it returns whether two systems connect. It is specific enough to be distinguished from general system-fact lookups, though it does not explicitly name sibling tools.

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 intended use is implied: call this tool to check data-exchange compatibility between two systems. However, it gives no explicit guidance about when to prefer this over sibling tools like renkeimap_compare, and it does not state any exclusions or alternative scenarios.

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 destructiveHint=false, and the description confirms 'Read-only,' so it doesn't contradict them. Beyond that it discloses genuinely useful behavior: the exact content of the response (route states + legend, verbatim vendor MCP URL rather than a search-found one, human steps, CLI add line, write_rules, citation) and the ambiguous-name candidate fallback.

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?

Effectively a single dense sentence with the core purpose front-loaded ('One call to connect or move data between two systems') before the output enumeration. It is packed with comma-separated detail but each item conveys real information, so it stays efficient despite the density.

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 appropriately carries the burden of describing the return contents, which it does thoroughly. For a read-only planning tool with fully covered parameters, an agent has enough to call it correctly; only the missing sibling differentiation keeps it short of complete.

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 all three parameters (from, to, agent) are already documented, making the baseline 3. The description adds only marginal meaning by explaining the effect of the agent param ('the answer then carries that CLI's add line', pass agent), but gives no extra detail on from/to beyond what the schema states.

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 (returns a plan to connect/move data between two systems in one call) and enumerates the concrete artifacts it produces (route states, official route, human steps, add line, write_rules). However, it never distinguishes itself from close siblings like renkeimap_connect, renkeimap_pair, or renkeimap_compare, so an agent can't tell which to pick from the description alone.

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 phrase 'One call to connect or move data between two systems' implies the use case, and 'Ambiguous names return candidates' hints at input handling. But there is no explicit when/when-not guidance and no naming of an alternative sibling, leaving the choice against renkeimap_connect/renkeimap_pair to inference.

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 read-only, non-destructive safety profile, so the bar is lower, yet the description adds meaningful context: the data is EXTERNAL third-party observation and expressly NOT the vendor's official announcement, plus it discloses the return composition. The mandatory disclaimer/citation relay is behavioral guidance the annotations do not convey.

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?

Dense but front-loaded: the core purpose leads, the return composition follows, and the mandatory relay directive is set off with ★. Every clause carries information, though the run-on colon-laden sentence is slightly heavy.

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 only one parameter, the description carries most of the return-value burden and does enumerate the response fields, plus a data-provenance caveat. It stops short of covering error/edge behavior (e.g., unknown slug), but is largely sufficient for calling the tool 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%, and the single slug parameter is already documented in the schema with an example and a pointer to renkeimap_find_system. The description adds no additional parameter 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?

States a specific verb+resource ('Current status of one system') and enumerates exactly what the result contains (closed-vocabulary conclusion, last-observed time, state bar, hour table, maintenance). It also distinguishes itself from renkeimap_status_history by scoping to 'Current', and from vendor announcements by flagging third-party observation.

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 implied by 'Current status of one system', and the ★ directive to always relay the disclaimer/citation is a genuine operational instruction. However, it never explicitly names when to choose this over renkeimap_status_history or renkeimap_system_facts, nor any exclusions or prerequisites beyond the slug source.

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 carry readOnlyHint/destructiveHint, so the bar is lower, yet the description still adds real value: it discloses data provenance ('the vendor's own records, not our observation'), the exact shape of what is returned (counts, monthly frequency, durations, weekday/hour patterns in JST, source URLs), and the empty-state sentinel found:false. It does not mention pagination or how the 1-30 limit interacts with the aggregates.

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 dense but front-loaded single sentence that leads with what the tool returns, followed by two short high-value fragments (Read-only; found:false meaning). Every clause carries information, though the parenthetical asides make it slightly heavy to parse in one pass.

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, the description carries the burden of describing returns and does so thoroughly — aggregate counts and frequencies, durations, weekday/hour patterns, recent records, and source URLs — plus provenance and the not-collected signal. An agent has everything needed to call and interpret this tool 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 coverage is 100%, so both slug and limit are already documented in the schema. The description only reinforces 'one system' (slug) and 'recent records' (limit) without adding format, constraints, or default behavior beyond the schema; 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 specific resource and scope: 'vendor-published incident history and announced maintenance for one system'. The word 'history' implicitly separates it from the sibling renkeimap_status, but the description never names that sibling or explicitly contrasts past-vs-current, so differentiation is left to the reader.

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: the caller must infer this is the tool for retrospective incident/maintenance data rather than current state. There is no explicit 'use this when...' or 'for live status use renkeimap_status' routing, though 'found:false = not collected yet' does hint at an empty-state condition worth knowing before calling.

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 destructiveHint=false, so safety is covered. The description adds the citation requirement ('Every response carries a citation line; when you use these facts in an answer, cite it') and specifies the data provenance (survey-dated, first-hand). This is useful behavioral context beyond the annotations.

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 with no waste. The primary purpose is stated first, then the citation instruction. Every sentence earns its place.

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?

The description lists the content categories and mentions sources and citation, which is sufficient for an agent to know what it will receive. Since there is no output schema, this compensates well. It doesn't detail error cases or pagination, but for a read-only facts tool this is adequate.

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 slug parameter is already documented in the schema. The description does not add any additional meaning to the parameter, just repeats the tool's purpose. 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 clearly states it returns 'First-hand, survey-dated facts about one system' and enumerates the types (auth method, rate limits, CSV surfaces, pricing pages). This is specific and distinguishes it from siblings like renkeimap_compare which implies multiple systems. The title is redundant but the description is clear.

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 implies usage by requiring a slug from renkeimap_find_system, indicating a prior step. However, it does not explicitly state when to use this versus alternatives like compare or find, nor does it state when not to use it. It gives context but no exclusions or explicit routing.

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