JustIdea Agency

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 value beyond that by disclosing the return format (Markdown full text) and the scope restriction that only published pages are reachable. It does not mention auth requirements or pagination/truncation behavior for long pages, which keeps it short of a 5.

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 sentences, front-loaded with the return value, then accepted input formats, then discovery guidance. The examples are concrete and each sentence carries distinct information 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?

With no output schema, the description correctly supplies the return format (Markdown full text) and the input scope. For a single-parameter read tool with annotations covering safety, nothing needed to invoke it correctly 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?

Schema coverage is 100% and the single url parameter is documented with a max length, so the baseline is 3. The description goes beyond that by giving two concrete accepted formats, a path ('/pl/cennik/sklepy-internetowe/') and an absolute URL, which clarifies the dual-input behavior the schema only hints at.

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+output format ('Full text of one justidea.agency page as Markdown') and enumerates the page types it covers (service, price list, profile, reviews, blog article). An agent can distinguish it from list_services and search_site without opening either 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?

Explicitly routes the agent: 'use list_services or search_site to find the URL', and constrains scope with 'Only pages published on the site'. This names the alternatives and the condition under which each is preferred, leaving nothing 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 and openWorldHint=false, so the safety profile is covered. The description adds valuable domain context beyond that: 12 categories each with packages, prices are net/VAT excluded and exactly as published. It does not mention pagination or response ordering, which is a minor gap.

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 sentences, front-loaded with what is listed and returned, followed by a useful price caveat and then sibling routing. 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?

No output schema exists, so the description carrying the return shape (price list plus service pages with short descriptions) and the VAT/currency caveat is exactly the right compensation. An agent has everything needed to call 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 coverage is 100% and the enum parameter already documents pl/en and the PLN vs EUR currency implication. The description adds no parameter-level detail, so the schema does the heavy lifting and a 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 (List) and resource (JustIdea Agency services) plus the exact data returned in scope (starting/from prices and links). The sibling tools get_page and search_site cover different content types, and the description makes the boundary explicit.

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?

Gives explicit routing: use get_page for the full scope of a service and search_site for city pages, case studies and articles. This names the alternatives and the condition that selects each.

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=true and openWorldHint=false already declaring safety and scope, the description adds useful context beyond annotations: the searchable fields, bilingual query support, and the shape of results. It omits pagination/limit behavior, which is left to the schema.

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 tight sentences, front-loaded with what is searched, then language support, then result shape and follow-up. No filler or repetition 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 no output schema, the description usefully names the return fields (titles, URLs, descriptions) and the next-step tool, covering the essentials for a 4-param search. It could say more about limit/result-count behavior to be fully 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 coverage is 75%, so kind, language, and query are already documented in the schema. The description adds the language behavior ('Polish and English queries both work') but contributes nothing on kind or limit beyond the enum, so it stays at baseline.

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 (search) and resource (justidea.agency pages) plus the fields searched (titles, descriptions, section headings), which is concrete and distinguishable from siblings like get_page and list_services. An agent knows exactly what this tool retrieves without opening the 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?

Clearly signals the follow-up path ('read a result with get_page'), routing the agent between search and retrieval. It does not state when not to use it versus list_services or send_inquiry, so it stops short of full explicit alternatives.

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 is a non-read-only, non-idempotent, open-world, non-destructive action. The description adds substantial context beyond that: the inquiry lands in a CRM and reaches the sales team, the sender receives a confirmation e-mail, a human replies within one business day, consent under a linked privacy policy is required, and there is a hard rate limit of 2 inquiries per e-mail per day.

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?

Front-loads the purpose, then layers in side effects, consent gating, budget interpretation, rate limits, and an escalation path. Despite its length, every clause carries operational weight for a compliance-sensitive mutation tool; there is 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?

With no output schema, the description compensates by describing what happens on success (CRM routing, confirmation e-mail, one-business-day human reply). Combined with annotations covering the safety profile and full schema coverage, an agent has everything needed to invoke this correctly and safely.

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 baseline is 3, but the description adds real meaning: budgets are PLN net with 'tys. zł' defined as thousand PLN, and zgoda is semantically a consent gate that may only be set true after the user agrees. These clarify interpretation beyond the schema text.

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 ('Send a sales inquiry to JustIdea Agency') plus the destination ('agency CRM and the sales team'), which immediately distinguishes it from the read-only siblings get_page, list_services, and search_site. An agent can tell this is the action/write tool without opening any 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?

Gives explicit when-to and when-not-to rules: it must only use details the user supplied, must never invent a name/e-mail/phone, must show the message and obtain consent before sending, and sets zgoda=true only after agreement. It also routes urgent cases to a phone number, covering the off-tool alternative.

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