Alexandre Caramaschi: cursos e aulas de GEO em português

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

Beyond the annotations, the description adds a crucial behavioral nuance: 'it never sends a message on the caller's behalf.' This prevents an agent from misusing the WhatsApp direct link by assuming the tool initiates contact. It also discloses the read-only nature in practical terms and describes what the response contains, adding real value over the raw hints.

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 purpose, then returns, then safety/no-arguments. The enumeration of channels is slightly detailed but earns its place because it sets agent expectations about the response. No wasted words.

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, annotation-covered, read-only tool with an output schema, the description is fully sufficient. It covers purpose, content of the response, the behavioral caveat, and argument requirements. Nothing an agent needs to call 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?

With zero parameters, the schema has nothing to document and the description confirms this with 'No arguments.' Baseline 4 applies for a no-parameter tool; the explicit confirmation removes any doubt about optional arguments.

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 opens with a specific verb+resource ('tell a person how to contact Alexandre Caramaschi') and enumerates exactly what is returned (WhatsApp link, e-mail, form URL, CTA). This clearly distinguishes it from all siblings, which cover business info, courses, content, and location — none of which provide contact channels.

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 opening phrase 'Use to tell a person how to contact Alexandre Caramaschi' gives a clear trigger condition for when to invoke the tool. It does not name explicit exclusions or alternatives, but the sibling set is sufficiently distinct that the usage 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 establish read-only, idempotent, non-destructive behavior. The description adds useful output context beyond that: the founder credential appears in invariant order, prices are in BRL with an as-of date, and the result is the practice profile rather than the company profile. It also clarifies a scope boundary without contradicting 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?

The trigger condition is front-loaded in the first sentence, followed by a dense but relevant enumeration of returned data. Every listed item adds value, though the long parenthetical list makes it somewhat harder to scan than a structured breakdown.

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-argument, read-only information tool with an output schema, the description covers the trigger, the returned content, pricing details, and the boundary with institutional data. Nothing an agent needs to call 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?

The tool has zero parameters and the schema already covers 100% of them. The description reinforces this with 'No arguments,' so an agent knows nothing needs to be supplied. With no parameters to document, the zero-parameter baseline of 4 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 opens with the exact use cases—who Alexandre Caramaschi is, what he offers and at what price, and how to reach his practice—and then enumerates the specific content returned. It also distinguishes itself by explicitly stating that Brasil GEO's institutional data is not served here. This is a clear, specific verb+resource description, not a tautology.

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 states when to use the tool: when an agent needs the person's identity, offerings, prices, or contact details. It also gives an explicit exclusion and alternative routing: 'Brasil GEO's own institutional data is served by brasilgeo.ai, not here.' This lets an agent select the tool without inspecting sibling schemas.

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 it readOnly, idempotent, and non-destructive. The description adds valuable behavioral context beyond that: it reports coverage ratio (null when denominator unknown), declares vs retrievable counts, and guarantees that courses without retrievable text are listed in gaps with a reason and 'nothing is silently dropped.' This is rich and accurate, with no contradiction.

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 critical usage directive and then lists exactly what the tool returns. It is a bit long, but every sentence carries distinct information (revision, normalization version, counts, ratio, per-course breakdown, gap behavior). 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 no-argument read-only tool with an output schema, the description is complete: it explains the purpose, when to call it, what it returns, edge cases (null ratio, gaps), and the guarantee that nothing is silently dropped. An agent has everything needed to invoke 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?

There are zero parameters, and the schema is an empty object with 100% coverage. The description explicitly says 'No arguments,' which is harmless but repeats the schema. With no parameters to explain, the baseline of 4 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 names a specific resource ('catalog manifest and coverage'), a clear verb ('returns the published revision...'), and a specific use ('Use first, before reading modules in bulk'). It distinguishes itself from bulk module-reading by stating it reveals what can actually be read, so an agent can tell it apart from getCourseModules/getModuleContent.

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 explicitly states when to use it ('Use first, before reading modules in bulk'), which is strong usage guidance. It does not explicitly name alternative tools or state when not to use it, but the pre-flight instruction is clear enough to route the agent correctly.

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 valuable behavioral context: the course-not-found response, the 'always free' price with service level and replacement policy, and the content.available flag indicating whether module text is retrievable through this server. It doesn't contradict 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 dense paragraph that front-loads the core purpose and then lists the return fields. It's longer than ideal but every sentence adds information about the return payload or behavior. The structure is logical: purpose, return contents, error case.

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 output schema exists, the description doesn't need to explain return values in detail, but it does anyway, which is helpful. It covers the error case, the price/service policy, and the content availability flag. For a read-only, single-parameter tool, this is 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 100%, so the schema already documents the slug parameter well. The description adds a useful cross-reference to listCourses as the source of the slug and gives an example ('seo-geo'), which helps the agent understand the expected format beyond the schema's regex-like description.

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 ('decide whether a course fits a learner') and resource ('one course'), and enumerates the exact data returned. It clearly distinguishes itself from siblings like getCourseModules and listCourses by focusing on the pedagogical ficha of a single course.

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 implies when to use it: when evaluating a course's fit for a learner, and it explicitly notes the 'course not found' response. It doesn't explicitly name sibling alternatives or exclusion conditions, but the purpose is clear enough that an agent can infer when to choose it over listCourses or getCourseModules.

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?

Even though annotations already mark the tool as read-only and idempotent, the description adds substantial behavior: it details error responses (course_content_unavailable with a list of readable courses, course_not_found) and enumerates the exact return fields including the sha256 and character length of module text. This goes beyond the annotation signal.

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 purpose, followed by return details, then edge-case behavior. Every sentence contributes distinct information with no redundancy or filler. The long enumeration is justified by the need to specify stable identifiers for downstream use.

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, idempotent tool with full schema coverage and an output schema, the description is complete. It covers the main use case, return contents, prerequisite courses, and both error scenarios. Nothing essential is missing 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?

The only parameter, slug, is fully described in the schema ('exactly as returned by listCourses, e.g. seo-geo'). The tool description does not add any extra meaning about the parameter, so the high schema coverage 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 starts with a specific verb and resource: 'get the reading order of a course and the identifiers needed by getModuleContent.' This clearly distinguishes it from siblings like getCourseDetails and getModuleContent. The extended return value list further clarifies the tool's role as a module-list provider.

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 explicitly says 'Use to get the reading order...' and notes that only courses marked contentAvailable in getCatalogManifest have modules, which is a clear precondition. It does not explicitly name an alternative for other course metadata, so it stops short of a full when-not-to-use statement.

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 the operation read-only, idempotent, and non-destructive. The description adds useful context such as 'No arguments' and the coverage statement scope, but it does not disclose behavioral details beyond what the annotations and simple return-value list imply. There is no contradiction.

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 states the purpose first, then the return fields, then the argument requirement. Every sentence adds information and 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?

For a zero-argument read-only tool with an output schema and supportive annotations, the description is complete. It tells the agent exactly when to use it, what it returns, and that no arguments are needed.

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 has zero parameters and the description explicitly confirms 'No arguments.' This fully eliminates any parameter ambiguity, so the description earns the baseline of 4 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 clearly states the tool's resource ('where the practice is based and where it serves') and enumerates the exact output fields (city, state, country, timezone, coordinates, coverage statement). It is unambiguous about the tool's function, though it does not explicitly contrast itself with siblings like getBusinessInfo or contactUs.

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 'Use for where the practice is based and where it serves' provides a clear, explicit use case. However, it does not mention when not to use this tool or name alternative sibling tools, so the guidance is context-rich but lacks 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?

Beyond the readOnly/idempotent annotations, the description discloses pagination semantics (partial completeness, range, nextCursor), error cases (invalid_cursor, module_not_found), a hash for integrity, and a prompt-injection caution that the text is data, not instructions. This is unusually rich and fully consistent with 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?

The description front-loads the action and then presents dense, non-redundant behavioral details in a logical order: output shape, pagination, errors, then safety. No sentence is filler, and the length is justified by the complexity of the pagination behavior.

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 that an output schema exists and annotations cover safety, the description covers everything an agent needs: return format, metadata, pagination, cursor continuation, error responses, and the security boundary around lesson content. There are no obvious gaps that would cause an incorrect call.

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 documents all four parameters at 100% coverage, so the baseline is 3. The description adds value by explaining cursor behavior across revisions, fragment boundaries at 40,000 characters, and how the hash relates to the full document, which helps an agent use cursor and maxChars correctly.

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 opening 'Use to read one lesson' names a concrete verb and resource, and the rest clarifies it returns the module text as Markdown with metadata. However, it never explicitly names a sibling tool (e.g., getCourseModules or searchContent) as the alternative, so sibling differentiation is implicit rather than 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?

The phrase 'Use to read one lesson' provides a clear reason for invoking this tool, and the note that module accepts an id/slug from getCourseModules hints at the listing prerequisite. It does not, however, state when to prefer alternatives like searchContent or getCourseDetails, so there are no formal 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?

Beyond the annotations (read-only, idempotent, non-destructive), the description details the exact data returned, including the CITATION.cff file and public knowledge base, and adds a caveat about the peer-review status of SSRN and Zenodo deposits. This gives the agent material context for correct handling of results.

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, all substantive: usage instruction, return payload with enough detail, and a quality caveat. It is front-loaded and contains no filler or redundant repetition of the schema.

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-argument read-only tool with an output schema, the description is complete. It covers the purpose, the content, the caveat about peer review, and confirms no arguments are needed. Nothing an agent needs to invoke and interpret the result 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 has zero parameters and schema coverage is 100%, so the baseline is 4. The description explicitly confirms 'No arguments,' which aligns with the empty schema and adds no unnecessary parameter detail.

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 identifies the tool as retrieving Alexandre Caramaschi's research publications, listing specific returned fields (ORCID, publication title, DOI, URL, venue, date, source, CITATION.cff, knowledge base). It is easily distinguished from sibling tools, which focus on courses, contact, and business info.

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 opens with an explicit usage instruction: 'Use to cite Alexandre Caramaschi's research.' It also provides a caution about SSRN and Zenodo not being peer-reviewed. It does not name alternative tools, but none of the siblings clearly overlap, so the guidance is 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 carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral value on top: the list is complete, needs no pagination, and takes no arguments — useful facts not derivable from the annotations or schema. 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?

Three tightly packed sentences, front-loaded with purpose before return format and invocation notes. Every sentence earns its place; there is zero filler 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 a zero-parameter surface, an existing output schema, and complete annotations, the description covers everything an agent needs: what it returns, where from, and that no pagination or arguments are required. Nothing is missing 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?

With zero parameters and schema coverage at 100% (empty schema), the baseline is 4. The description appropriately states 'No arguments' and explains why (complete list, no pagination), which fully removes any doubt about invocation. Nothing more could be demanded here.

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 (discover/list) and resource (free courses at alexandrecaramaschi.com/educacao) and is clearly distinguishable from siblings like getCourseDetails, which fetches a single course by slug. The return payload is spelled out (hub URL, course count, per-course slug/title/track/level/canonical URL), leaving no ambiguity about what this tool is for.

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?

Offers clear when-to-use guidance: deploy this tool 'before asking for one by slug,' which establishes the discovery-then-fetch flow relative to getCourseDetails/getCourseModules. It does not explicitly name the alternative tool or state exclusions, but the contextual cue is sufficient for an agent to route correctly.

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 as read-only, idempotent, and non-destructive, and the description adds substantial behavioral detail: results are literal passages, never generated answers; no match returns an empty list; the search is lexical (BM25 over Portuguese stems); and passage text is explicitly framed as data, not instructions. This last point is a valuable security-oriented behavioral disclosure.

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 information-dense and front-loaded with the primary purpose. While it is a long, single-paragraph run-on in places, every clause contributes either behavioral, error-handling, or security-relevant detail, and there is no filler or tautology.

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 search tool with rich annotations, a 100%-described schema, and an output schema, the description covers the core purpose, result semantics, matching algorithm, error conditions, coverage behavior, and a prompt-injection caution. An agent has everything needed to invoke 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 description coverage is 100%, so the input schema already documents query, slug, and limit. The description mostly restates these semantics (e.g., 'natural-language question or keywords', 'accents are optional; stems are matched') rather than adding new parameter meaning, so the baseline 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 opens with a specific verb and resource: 'Use to find where the courses talk about something before reading whole modules.' It clearly defines the tool as a cross-course/module passage search and distinguishes it from content-retrieval siblings like getModuleContent by emphasizing search-before-reading. The detailed return-value list further pins down exactly what the tool produces.

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 states the intended use case ('before reading whole modules') and clarifies that only courses with retrievable text are searched, with explicit error behaviors for unavailable text and unknown slugs. It does not name sibling tools as alternatives or provide explicit when-not-to-use conditions, but the context is clear enough for an agent to select it appropriately.

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