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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered structurally. The description adds that execution spans all rules and that output is prioritized and Turkish, but says nothing about runtime cost, rate limits, or whether the run has side effects on the underlying data.

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 no filler, which is structurally clean. But for a tool that aggregates seven sibling domains with three undocumented thresholds, this level of brevity is under-specification rather than conciseness.

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?

An output schema exists, so return values need not be explained, but that is the only gap covered. The three tuning parameters are undocumented and there is no routing guidance against seven siblings, leaving an agent unable to call this correctly without guessing.

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 0% and the description documents none of the three parameters (low_stock, sla_hours, return_cluster_min). Their defaults (5, 48, 3) are visible but their meaning and units are left entirely unexplained, so the description fails to compensate for the coverage gap.

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 verb ('çalıştırır' / runs) and a deliverable ('önceliklendirilmiş Türkçe aksiyon listesi' / prioritized Turkish action list), which conveys the aggregate nature of the tool versus the single-concern siblings. However, 'tüm kuralları' (all rules) is undefined and never connects to the sibling domains (orders, returns, SLA, stock, reviews, prices), so an agent cannot tell exactly what is being aggregated.

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 when-to-use guidance, no mention of when to prefer this digest over the individual sibling tools (list_orders, sla_breaches, stock_alerts, etc.), and no prerequisites stated. The agent must infer that this is the umbrella tool from the name 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, idempotentHint=true, destructiveHint=false, and openWorldHint=true; the description's "Salt okunur" (read-only) merely restates the annotation rather than adding context. Nothing is said about what "recent" means, the default page size behavior, or any rate/scope limits.

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 short sentences, front-loaded with the action and scope, with no filler. It is efficient, though the brevity edges toward under-specification rather than pure conciseness.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. However, with three undocumented parameters and no detail on date format, status values, or paging, the definition is only minimally 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 0%, so the description carries the full burden, yet it only alludes to two of three parameters ("durum ve tarih" = status and date) and gives no format for the date value or accepted status values. The limit parameter is never mentioned at all.

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 ("Son siparişleri listeler" = lists recent orders) and scopes it with the available filters. It does not differentiate itself from the closest sibling, list_returns, which follows the identical listing pattern, 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?

The parenthetical mentions that status and date filters exist, but never says when to reach for this tool versus list_returns, daily_digest, or price_overview. No exclusions, prerequisites, or alternative-routing guidance 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?

'Salt okunur' (read-only) merely restates the readOnlyHint annotation rather than adding context. With annotations already covering readOnly, idempotent, openWorld, and destructive hints, the description contributes nothing new about pagination, default result size, or rate limits.

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 short sentences with no filler, and the core purpose is front-loaded. It is concise, though brevity here reflects missing content rather than disciplined editing.

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?

An output schema exists so return values need no explanation, but the definition omits any guidance on the undocumented 'since'/'limit' filters and gives no usage context. For a list tool with unlabeled parameters, this is incomplete.

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?

Both parameters (limit with default 50, since) have 0% schema description coverage, and the description does not mention either one. The meaning of 'since' (date format? timestamp? cursor?) is left entirely undocumented.

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: 'listeler' (lists) applied to 'İade ve talep kayıtları' (returns and request records). This distinguishes it reasonably from the sibling list_orders, though it does not explicitly name the distinction.

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 gives no when-to-use guidance, no prerequisites, and does not mention any alternative among the many listing siblings (list_orders, stock_alerts, return_clusters). An agent must infer selection entirely from the tool name.

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, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is fully covered. The description adds useful scope detail by defining what counts as an inconsistency (above-list price, unusual discount), but says nothing about severity, thresholds, or grouping of findings.

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 sentence that front-loads the verb and resource and uses the parenthetical only to sharpen scope. No filler, no restatement of the name.

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 parameters, an output schema present, and annotations covering the safety profile, the description only needs to convey scope — which it does by naming the anomaly types. It is slightly thin on how findings are surfaced, but nothing essential for invoking it 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 there is nothing for the description to disambiguate; baseline 4 applies. Schema coverage is reported as 100% with an empty properties object.

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?

Names a specific verb (raporlar/reports) and a specific resource (fiyat tutarsızlıkları/price inconsistencies), and even enumerates the two anomaly classes it covers (price above list, unusual discounts). It is clearly distinguishable from siblings like stock_alerts or sla_breaches by topic, though it never explicitly contrasts itself with them.

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 parenthetical examples imply when this tool is relevant — when looking for pricing anomalies — but there is no explicit when-to-use, when-not-to-use, or reference to an alternative such as daily_digest. Usage must be inferred from the anomaly types listed.

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, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds that the tool performs a clustering/aggregation over a time window rather than a raw read, but says nothing about result shape, thresholds, or performance characteristics beyond what the annotations provide.

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 zero filler, and the clustering intent plus the parenthetical root-cause gloss arrive immediately. It is arguably too terse for a tool with 0% schema coverage, but as structure goes it is efficient and well-ordered.

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?

An output schema exists, so return values need not be described, and the annotations cover the safety profile. What remains missing is parameter meaning (notably min_count) and any indication of how clusters are keyed, which leaves the definition only marginally complete for a zero-coverage schema.

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 0%, so the description carries the full burden. It gestures at the 'days' parameter with 'Son N günde' but never ties it to the argument name or explains the default of 30, and it completely ignores 'min_count' (default 3), which controls how many repeats are needed to form a cluster – a critical semantic for interpreting results.

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 verb and resource ('aynı nedenle tekrarlayan iadeleri gruplar' – groups returns that repeat for the same reason) plus a temporal scope, and the 'iade kök nedeni' (return root cause) gloss makes the output intent unambiguous. It is clearly distinguishable from the sibling list_returns, though it never names that sibling 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?

The description embeds its own use case – finding returns that recur for the same root cause – which implies when an agent should reach for it instead of a plain listing. However, it gives no explicit when-to-use/when-not guidance and never mentions alternatives such as list_returns, so the routing decision is left 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuine value by defining what counts as a breach (prep-time overrun or passed delivery promise), but it says nothing about scope, filtering behavior, or how the 48-hour default is applied.

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 no filler; every word carries the breach definition. Nothing is repeated from the schema or annotations.

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?

An output schema exists, so return values need not be described. However, the sole input parameter's meaning is left unexplained in both schema and description, which is a real gap for a threshold-driven query tool.

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 0% and the description never mentions 'sla_hours' or explains what the default of 48 measures or applies to (prep time vs. delivery promise). With a single undocumented threshold parameter that materially changes the result set, the description fails to compensate for the schema gap.

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 verb ('bulur' / finds) and a specific resource set (orders that exceed preparation time or have passed their delivery promise), which is meaningfully more precise than a generic 'list orders'. It is distinguishable from siblings like list_orders, though it does not explicitly name or contrast with any of them.

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 call this tool versus list_orders, stock_alerts, or daily_digest, and no stated prerequisites or exclusions. The agent must infer the trigger condition entirely from the one-line definition.

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, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds one genuine behavioral fact beyond that – results are sorted with depleted items first – but says nothing about how the threshold is applied, whether results are live or cached, or how large the result set can be.

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 front-loaded sentence with no filler; the scoping condition and the sort order are both packed in efficiently. It is arguably too short for the amount of undocumented behavior it leaves behind, but as a matter of structure there is no waste.

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?

An output schema exists, so return values need no explanation, and the read-only nature is covered by annotations. However, with a fully undocumented parameter and no guidance on when to reach for this tool, the definition is only minimally sufficient for a one-parameter alert query.

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 0% for the single 'threshold' parameter, so the description must carry that burden and does not. It gestures at the concept of a stock threshold but never explains the unit, that the default is 5, or what happens when the parameter is omitted.

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: it returns products that have fallen below a stock threshold, and adds the ordering rule (out-of-stock items first). That is concrete enough to distinguish it from unrelated siblings like list_orders or price_overview, though it never names or contrasts a sibling 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?

Usage is only implied by the subject matter (call it when you want low-stock or depleted products). There is no statement of when to prefer this over a general product listing, no prerequisites, and no mention that the threshold parameter can be tuned to change the result set.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered. The description adds no additional behavioral context beyond implying a search operation. It does not describe what happens if no reviews are found, nor does it explain the 'hours' parameter's role. With annotations covering safety, the description adds minimal value, hence a 3.

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 a single short sentence with zero waste. It is front-loaded with the core purpose. While concise, it sacrifices necessary detail, but that is not a structure issue per se.

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?

Given the presence of an output schema, return values need not be explained. However, the tool has one undocumented parameter and no usage guidelines. For a tool that likely involves filtering and time windows, the description is incomplete; it does not explain the 'hours' default or what constitutes 'unanswered' or 'negative'. It leaves key context 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?

Schema description coverage is 0%, so the schema field 'hours' has no description at all. The tool description does not mention the 'hours' parameter or its meaning (e.g., lookback window). With one parameter completely undocumented, the description fails to compensate for the low 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 states a specific verb+resource: finding unanswered negative product reviews. It is clear what the tool does. However, it does not differentiate from sibling tools like sla_breaches or stock_alerts at all. Without sibling differentiation, a 4 is appropriate.

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 tool versus alternatives such as list_orders or sla_breaches. The description does not explain the context or conditions under which unanswered reviews should be checked. It implies usage but provides no explicit when/when-not guidance.

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