Gus Dantas · retail media measurement

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

With no annotations provided, the description carries the full burden and excels: it discloses that questions are stored in full, details what other data is recorded, and instructs the agent to answer only from returned passages. This is substantial behavioral context.

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 clarifies the response format, and ends with a crucial privacy note. Every sentence serves a distinct purpose without redundancy, striking an excellent balance between detail and brevity.

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 one-parameter tool with no output schema, the description adequately covers the return value, usage constraints, and privacy implications. It provides enough context for an agent to select and invoke the tool correctly, and the sibling tools do not weaken this completeness.

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 the single parameter fully ('The question, in the asker's own words'), but the description adds value by specifying acceptable topics and privacy restrictions, enriching the parameter's meaning beyond the schema 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?

The description uses a specific verb 'Ask' with a clear resource 'Gus Dantas', enumerates example topics, and states the return value ('relevant passages he has written'). This clearly distinguishes the tool from siblings like gus_profile or retail_media_primer.

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 context for when to use the tool (any question about Gus) and offers an alternative (ghostavo.com) for privacy-conscious users. It also warns against confidential information, giving some exclusion criteria, though it doesn't explicitly contrast with sibling tools.

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 no annotations provided, the description carries the full burden of behavioral disclosure, but only describes the content of the profile, not the operation itself. It does not explicitly state that this is a read-only retrieval or indicate any side effects, output format, or safety profile.

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, compact sentence that front-loads the purpose ('A short professional profile') and uses a colon to enumerate the content areas. Every word earns its place with no redundancy or 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 simple parameterless tool with no output schema, the description adequately outlines the returned content (where he works, what he has done, what he is doing now). It could slightly improve by explicitly stating the operation type (e.g., 'returns'), but it is largely complete for its narrow scope.

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 coverage is trivially 100%. The description does not need to explain parameters, and per the rubric, a baseline score of 4 applies for parameterless tools.

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 resource (Gus's profile) and specifies the content areas (where he works, what he has done, what he is doing now). It distinguishes itself from sibling tools like ask_gus by indicating this is a static profile rather than a conversational query, though it lacks an explicit verb like 'returns' or 'displays'.

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 alternatives. The description merely states what the profile contains, leaving the user to infer that this is for retrieving a professional profile, but no when-to-use or when-not-to-use context is provided.

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 no annotations, the description carries the full burden. It discloses that Gus reads the message himself and replies to the included contact detail, which is important behavioral context. It also sets expectations about consent and fidelity when sending on behalf of others, adding value beyond a simple 'send' action. However, it does not detail any side effects, storage, or delivery mechanics, hence not 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 primary action ('Send Gus a message'), and every sentence adds relevant detail. There is no wasted text, and the consent instruction is concisely integrated.

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 zero annotations, no output schema, and only three simple parameters, the description is comprehensively complete. It explains the tool's purpose, use cases, recipient behavior, reply mechanism, and ethical usage. No critical gaps remain for an agent to correctly select and invoke the 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?

The input schema covers all three parameters (name, contact, message) with descriptions. The tool description adds minor extra meaning by noting that replies go to the contact detail, but otherwise relies on the schema. With 100% schema coverage, a 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 clearly states 'Send Gus a message' with a specific verb and resource. It further specifies the purpose (work enquiries, questions not covered by written answers, corrections) and distinguishes from sibling tools like ask_gus by mentioning 'questions his written answers did not cover.'

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 states when to use: 'for work enquiries, questions his written answers did not cover, or a correction.' Also provides clear instructions for sending on behalf of others ('Ask the person before sending on their behalf, and send their words rather than a summary'), which serves as a usage guideline and exclusionary note.

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 no annotations provided, the description carries the burden of disclosing behavior. It states it's a 'plain explanation,' which implies a read-only, informational response. It doesn't explicitly mention lack of side effects, but for an educational primer the behavior is clearly non-mutating and self-contained.

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 extremely concise, consisting of two sentences that front-load the core purpose and list specific content points. Every word earns its place, with no filler or repetition.

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 informational tool with no parameters, no output schema, and no annotations, the description fully covers what the tool is, what topics it addresses, and even provides a usage note. No critical information 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, so the description has no obligation to explain parameter meanings. The baseline of 4 applies here since schema coverage is trivially complete and there are no parameters to clarify.

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 providing a plain explanation of retail media, enumerating specific topics (three channels, recording capabilities, loop concept). It is distinct from sibling tools like ask_gus or gus_profile, which likely focus on Gus, by explicitly framing this as a conceptual primer.

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 'Useful even if you have no interest in Gus' implies the tool is for learning retail media fundamentals independently of the Gus context. While it doesn't explicitly state when to use this over siblings, the description gives a clear contextual trigger (wanting an explanation of retail media) and subtly contrasts with Gus-focused tools.

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