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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable context beyond annotations by detailing the exact data returned (operator, risk label, DNO status, white list, counters) and explains a nuanced behavior: DNO numbers indicate spoofing. It also cites the data source (numertel.pl), which is useful for trust assessment. This goes beyond a mere statement of safety.

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, using two sentences to convey purpose, usage triggers, and output details. It is front-loaded with the action ('Sprawdź reputację') and organized logically: action first, then when to use, then return elements. Every clause adds relevant information without redundancy or fluff.

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-parameter read-only lookup tool with a rich output schema and strong annotations, the description covers all necessary aspects: what the tool does, when to use it, what it returns, and even a caveat about DNO/spoofing. It is comprehensive enough for an agent to select and invoke the tool correctly without additional context.

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 schema covers 100% of parameter semantics with a description for 'number' that mentions format, accepted +48 prefix, and spaces being removed. The tool description adds little extra beyond restating that it handles Polish numbers, since the schema already provides detailed formatting guidance. The baseline of 3 is appropriate when the schema does the heavy lifting.

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: 'Sprawdź reputację polskiego numeru telefonu' (check the reputation of a Polish phone number). It also lists specific user queries that should trigger use, such as 'kto dzwonił' (who called) or 'czy numer to spam/oszustwo' (is the number spam/scam), which distinguishes it from sibling tools like check_scam_domain and find_official_number.

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 explicitly provides when-to-use guidance: 'UŻYJ, gdy użytkownik pyta: kto dzwonił, czy numer to spam/oszustwo, czy telefon rzekomo z banku lub urzędu jest prawdziwy.' This is clear and actionable. However, it does not explicitly mention when not to use this tool or name alternative tools, though the sibling list and the described features imply appropriate use cases.

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 establish readOnly and idempotent behavior, so the description adds valuable extra context: the verdict is deterministic ('Werdykt deterministyczny, zero LLM') and the data sources are clearly attributed (CERT Polska, NumerTel, numertel.pl). It also discloses recognition of obfuscated formats, which helps set expectations. No contradiction with 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?

The description is dense but well-structured, front-loading the core action, then usage trigger, then acceptable inputs, then behavioral guarantees. Every sentence earns its place: it packs purpose, scope, examples, and data provenance without fluff or redundancy.

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 tool's moderate complexity, the presence of an output schema, and the readOnly/idempotent annotations, the description covers all essential aspects: what it checks, when to use it, what inputs it accepts, how it behaves (deterministic), and where its data comes from. It does not need to explain return values because the output schema exists.

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?

Although the schema already documents the 'text' parameter well, the description meaningfully enriches it by explaining accepted input forms (single domain, URL, email, number, or entire message) and how obfuscated formats are handled (evil[.]pl, hxxp://, +48). This goes beyond the schema's basic type description and gives the agent practical guidance for what to pass.

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 a specific verb-resource pair: checking pasted suspicious messages against CERT Polska's warning list and NumerTel phone database. It explicitly lists the artifact types (domains, links, emails, phone numbers) and distinguishes itself from the phone-only sibling tool by handling whole messages and multiple entity types.

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 provides an explicit trigger condition: 'UŻYJ, gdy użytkownik pyta: czy ten link/strona/mail jest bezpieczny...' This is strong when-to-use guidance. However, it does not mention when not to use it or name alternative sibling tools (e.g., check_phone_number) for phone-only queries, so it lacks explicit exclusions.

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 and idempotentHint, so the safety profile is covered. The description adds a meaningful behavioral detail: it returns the same data as check_phone_number plus a link to the number's page. However, it doesn't describe error handling or edge cases, which is acceptable given the low complexity and annotation coverage.

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 two sentences, front-loaded with the primary action, and contains no fluff. Every word serves a purpose, and it remains concise while conveying key details about input and output.

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 tool's simplicity (1 parameter, annotations present, no output schema), the description is sufficient. It explains the input source and the output relationship to check_phone_number, providing enough context for an agent to use the tool correctly. Slight deduction for not detailing the exact return structure, but this is mitigated by the 'same data as check_phone_number' reference.

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 schema has 100% coverage for the single parameter 'id', and the description essentially repeats what the schema already states (Polish number, 9 digits). No additional semantic value is added beyond the schema, 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 clearly states the tool's function: fetching a full number reputation card by ID returned from search. It also specifies the ID format (9 digits) and distinguishes this from check_phone_number by noting it returns the same data plus a link to the number's page.

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 indicates when to use this tool (after obtaining an ID from search) and contrasts it with check_phone_number, implying this is a more complete variant. While it doesn't explicitly mention alternatives or exclusions, the context provides sufficient 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?

Annotations readOnlyHint and idempotentHint are present. The description adds value by detailing the return data (new domains, UKE list size, official warnings) and noting open data source (CC-BY). No contradiction with 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?

The description is a single paragraph that efficiently conveys purpose, usage, and output. It front-loads the key verb and resource, and every sentence adds value without redundancy.

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 tool has one parameter, annotations, and an output schema, the description covers all necessary aspects: purpose, usage context, return data, and data source. It is complete for its role as a statistical aggregation 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 coverage is 100% with a single parameter 'days' fully described in the schema. The description does not add further parameter details beyond what the schema provides, so baseline score of 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 title and description clearly state the tool provides current phone abuse indicators in Poland. It specifies exactly what data is returned (new domains, UKE list size, official warnings) and explicitly instructs when to use it (user asks about scam scale or new fraud campaigns), distinguishing it from sibling tools like check_phone_number or check_scam_domain.

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 explicitly says 'UŻYJ, gdy użytkownik pyta o skalę oszustów, phishingu lub spamu w Polsce albo co nowego w kampaniach oszustów', providing clear context for use. While it doesn't specifically state when not to use it, the focus and sibling context make the guidance sufficient.

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 idempotentHint=true, so the safety profile is covered. The description adds valuable behavioral context: it specifies the Polish number format, the 'White List' source for verified official numbers, and that results contain id, title, and url. This goes beyond the annotations without contradicting them.

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 two sentences, front-loaded with the core action ('Search in NumerTel database'), and contains no wasted words. It efficiently communicates the two modes and the result structure.

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 a single parameter, no output schema, and good annotations, the description fully compensates for the missing output schema by stating the result fields. It also mentions the verified nature of the official numbers. No crucial information is missing for a tool of this simplicity.

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 schema already provides 100% coverage for the query parameter, including examples ('mBank', 'ZUS'). The description repeats essentially the same information (number or institution name) without adding new semantic details. Since the schema does the heavy lifting, a baseline score of 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 clearly states that the tool searches the NumerTel database, with two distinct modes: searching by Polish phone number to get a reputation card, or by institution name to get verified official numbers. It explicitly mentions the result fields (id, title, url), making the tool's purpose unambiguous and differentiated from siblings like check_phone_number.

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 provides clear guidance on when to use the tool: when a phone number or institution name needs to be looked up in the database. It outlines the two types of queries accepted. However, it does not explicitly contrast with sibling tools such as check_phone_number or find_official_number, so it stops short of a full when-not/alternatives explanation.

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