KnockWatch

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

The annotations already establish that this is a read-only, non-destructive, closed-world operation. Beyond those annotations, the description adds useful behavioral context: it is a public record, covers recent 30-day signals and outcomes, and includes Upbit and Binance status notices. It does not discuss freshness guarantees or rate limits, but those gaps are minor here.

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 front-loaded with the core purpose, then enumerates the specific record contents. It is somewhat long, but the detail is relevant because there is no output schema, and the bilingual structure remains readable.

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?

Because there is no output schema, the description carries the burden of explaining return values, and it does so thoroughly by listing signals, outcomes, warning flags, delisting dates, and listing-age checks. The main missing piece is routing guidance versus sibling tools, which prevents a perfect score.

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 parameter already documents that it accepts Upbit KRW-market symbols or Korean names with examples. The description confirms the one-coin scope but adds no parameter meaning beyond the schema.

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 that it shows a public KnockWatch record for one Upbit KRW-market coin, and it lists the specific signals, flags, dates, and notices returned. It is clear about scope, but it does not explicitly distinguish itself from sibling tools such as recent_signals or signal_record.

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 one-coin scope implies usage for checking a specific Upbit KRW-market coin. However, the description gives no explicit when-to-use, when-not-to-use, or alternative-tool guidance, despite having several sibling tools that an agent must choose between.

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 this as a read-only, closed-world, non-destructive operation. The description adds useful context that the output is one line per published statistic and includes period and source, but it does not describe ordering, limits, freshness, or formatting beyond that.

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 short and front-loads the core purpose before listing the content types. The bilingual repetition is mildly redundant but not confusing, and no sentence is wasted.

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 no-parameter, read-only tool without an output schema, the description gives an adequate picture of the returned content: per-signal historical results and exchange alert cases with period and source. It could be more complete by clarifying how this archive relates to the sibling signal tools.

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 has zero input parameters, so there are no parameter semantics to clarify. The empty schema is consistent with the description, which presents this as a no-argument reference listing.

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 resource: statistics KnockWatch has already published, including per-signal historical results and exchange alert cases with period and source. It is clear what the tool returns, but it does not explicitly distinguish itself from siblings such as recent_signals or signal_record.

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 guidance on when to use this tool versus the available alternatives. The phrase 'already published' implies historical reference use, but the description does not state when-not to use it or name any sibling 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 a safe read-only, closed-world operation, and the description adds meaningful behavior beyond them: only alerts that made it into the public channel digest are returned, so results lag the paid real-time feed, and outcomes are measured against the market. That freshness/latency constraint is exactly the kind of context annotations cannot 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?

The core purpose and the returned fields are front-loaded, and the latency caveat lands last where it matters. The Korean and English versions are near-duplicates, which adds length but serves a bilingual audience and costs little.

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 read-only list tool with no output schema, the description covers purpose, ordering, returned fields, and data-freshness limits. Only the pagination/limit behavior and how outcomes are computed are left thin, which are minor 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?

There is a single optional parameter with 100% schema description coverage, so the schema fully documents the count and its 1-20 bounds. The description adds nothing about the limit, which is acceptable given the coverage baseline of 3.

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 ('show recent public KnockWatch signals, newest first') and enumerates the returned fields (alert time, coin, outcome vs. market). It does not explicitly contrast itself with siblings like signal_record or signal_guide, so it stops 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?

Usage is implied by 'latest public signals' and the latency note steers agents who need real-time data elsewhere, but no alternative tool is named and no when-not condition is stated. An agent must infer that signal_record is the tool for older/detailed records.

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 openWorldHint=false, so safety behavior is covered. The description adds useful content context by naming the specific information disclosed (limits, alert start date), but discloses nothing about output shape or whether the guide is static or dynamic.

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 short and front-loaded, stating what each signal shows and then the limits and start date. The Korean and English lines are near-restatements of each other, which adds mild redundancy, but the core content is efficient.

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 reference tool with no output schema, the description is sufficient to know what it provides. It could improve slightly by saying whether the guide covers all signals or a subset, but nothing critical for 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?

The tool takes zero parameters and the description introduces none, so there is no parameter meaning to explain. The baseline of 4 applies for a parameterless tool.

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 resource and content: it explains each KnockWatch signal, which coin it points to, its reference source, its limits, and the alert start date. An agent can tell this is a reference/explanation tool rather than a data-retrieval tool. It does not, however, explicitly distinguish itself from siblings like facts or signal_record.

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 of alternatives such as check_coin or recent_signals, and no statement of prerequisites. Usage must be inferred from the word 'guide' alone.

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 openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context — that results are partitioned by pre-launch backtest versus post-launch actual alerts with periods, and that figures reconcile with knockwatch.co.kr/record. It says nothing about update cadence, aggregation windows beyond 'period', or sample-size caveats.

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 content statement is front-loaded and compact, with the key concept (cumulative outcomes and the period split) in the first sentence. The Korean and English versions are near-duplicates, which is justified for bilingual audiences but slightly redundant; nothing is padding beyond that.

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 one optional enum parameter, no nested objects, and no output schema, the description carries exactly the burden it needs to: what the numbers mean, how they are partitioned, and that they match a known reference page. An agent has enough to call it correctly 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 description coverage is 100% and the single optional enum parameter is fully documented in the schema, including the omit-for-both behavior. The description adds no syntax, defaulting, or semantic detail beyond that, 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 names a specific resource and view: cumulative per-signal outcomes expressed as 'M of N cases below market', split into pre-launch historical and post-launch actual alert periods. It is clearly an aggregate-record retrieval rather than a live signal feed, which implicitly separates it from recent_signals. It stops short of naming siblings explicitly, so differentiation is inferential 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?

Usage is only implied: an agent can deduce this is the tool for historical hit-rate totals, and the pre-/post-launch split hints at the appropriate context. There is no explicit when-to-use, when-not-to-use, or 'use X instead' routing against check_coin, facts, recent_signals, or signal_guide.

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