MadBroad Media

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

Annotations declare a non-read-only, open-world, non-idempotent, non-destructive write; the description usefully adds the downstream side effect (a personal editing-test link is emailed to the applicant) and the data-provenance constraint, which annotations cannot express. It stops short of stating duplicate-submission behavior despite idempotentHint=false, or what the caller receives on success.

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 short sentences, front-loaded with what the tool does, then the side effect, then the data constraint. No filler and nothing repeated from structured fields.

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 an 8-parameter, non-idempotent submission tool with no output schema, the description covers purpose, side effect, and provenance but leaves out what an agent would want before calling: the role of the optional notes field, duplicate-submission handling, and the shape of a success response.

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 50%: location, software, experience, and portfolioUrl are documented in the schema, while name, email, phone, and the optional notes are not. The description adds a meaningful constraint that all values must come from the applicant rather than being invented, but it does not clarify the four undescribed parameters, so it only partially compensates.

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 and resource ('Apply for MadBroad's video editor role') and anchors it to a known external form, so an agent can tell instantly this is the submission tool rather than the lookup siblings (get_role, list_open_roles).

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 implied by the role-specific naming and the constraint 'Only use details the applicant has provided,' but there is no explicit when-to-use/when-not, no mention of prerequisites (e.g., confirm with the applicant before submitting), and no exclusions relative to list_open_roles or get_role.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds that the payload includes FAQ-style and location content, which helps an agent anticipate what comes back, but it says nothing about whether the data is static or how large the response is.

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 short clause listing the four content areas with zero filler, front-loaded on the most important topic (what the company does). It's a fragment rather than a sentence, but no wording is wasted.

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 read tool with no output schema, the description should sketch the shape of the returned content; listing sections partially does this but never says whether the answer is prose, structured fields, or FAQ pairs. It is adequate but leaves an agent guessing about the response format.

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 the baseline is 4 and there is nothing the description could clarify about inputs. The description correctly implies a no-argument, fetch-everything call.

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 enumerates the concrete content areas the tool returns (what the company does, how it works, shooting locations, FAQ), which goes beyond the tautological title 'About MadBroad'. It's clearly a static company-info resource and is distinguishable from siblings like list_case_studies or get_role, though it lacks an explicit verb.

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 versus alternatives — nothing says to use it for general company questions rather than request_sales_call or list_open_roles. Usage is only inferable from the content list, and no exclusions or prerequisites are stated.

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, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds that the payload includes application instructions, which is useful context, but says nothing about error behavior for an unknown slug or how large the returned description is.

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 what the tool returns and followed immediately by the parameter source. No filler, though the phrasing 'Full description of one role' is slightly compressed compared to a clean verb-plus-resource statement.

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 one-parameter read-only lookup with annotations covering the safety profile and no output schema, the description plus schema give an agent enough to call it correctly. The main omission is failure behavior for an invalid or stale slug.

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 0% — the slug field has no description at all — so the description must carry the meaning, and it does by identifying slug as a role identifier obtained from list_open_roles. It stops short of giving format details such as casing or hyphenation, which leaves a small 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 names a specific resource ('one role') and scope ('Full description ... and how to apply'), which distinguishes it from the sibling list_open_roles that returns many. It does not state an explicit verb like 'retrieve', but the intent is unambiguous.

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 gives clear routing guidance: 'Use a slug from list_open_roles,' telling the agent to call the list tool first and where the identifier comes from. There is no explicit when-not guidance, but a single-role lookup has few plausible alternatives here.

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, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds that results link out to full write-ups, but says nothing about result count, ordering, or completeness of the list.

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 redundant or filler wording. Every clause (published results, links to write-ups) contributes useful information.

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, read-only listing tool with no output schema, the description covers what is returned and roughly what the payload contains. Only minor gaps remain (scope/freshness of the published results), which are low-stakes here.

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, which is the baseline-4 case; there is nothing for the description to clarify. The description correctly implies no filtering input is needed.

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 resource ('Published MadBroad client results') and its payload ('links to the full write-ups'), so an agent knows it retrieves case studies. It is clearly distinct from the sibling tools (company overview, roles, sales call), 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?

Usage is only implied: the content (client results, write-ups) suggests marketing/proof-point requests, but there is no statement of when to prefer this over get_company_overview or request_sales_call. No exclusions or prerequisites 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and a closed-world dataset, so the safety profile is fully covered. The description adds genuine value by disclosing the shape of each entry (location, pay, link), but says nothing about result volume, ordering, or whether the list can be empty.

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 sentence, front-loaded with the resource and followed by the payload contents. Nothing in it is 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 parameters, no output schema, and full annotation coverage, the description supplies enough for an agent to call it and know what comes back. The only gaps are listing behavior details such as pagination or ordering, which are minor for a static company careers list.

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 no parameter semantics to explain and the baseline of 4 applies. The description does not waste space restating an empty schema.

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 the resource precisely ('Every open role at MadBroad') and previews the returned fields (location, pay, link). It contrasts implicitly with the singular 'get_role' sibling by enumerating roles rather than fetching one, though it never states that contrast outright.

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 when-to-use guidance and no mention of alternatives such as get_role for a single posting or apply_video_editor for the application step. An agent must infer from the sibling names that this is the browse-then-fetch entry point.

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 openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is partly covered. The description adds genuine value beyond that: it discloses the data goes to an external sales team via a known form, that the result is a scheduling link rather than a confirmed booking, and the 'only use provided details' consent constraint. It stops short of saying whether the lead is emailed, stored, or how long the link is valid.

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 sentences with no filler: the action and outcome come first, the data-provenance constraint second. Nothing repeats the title or the schema, and the parenthetical URL is short and load-bearing.

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 seven-parameter mutation with full schema coverage and no output schema, the description covers what it does, where the data goes, what the caller receives (a link), and the consent constraint. A minor gap remains around post-submission behavior (confirmation, follow-up, failure modes), which an agent handling an external side effect would benefit from knowing.

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% and all seven fields carry per-field descriptions with enums, so the schema does the heavy lifting. The description adds only the aggregate framing ('a brand's details') and the provenance rule, not field-level meaning beyond what is already documented.

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 ('Submit a brand's details to MadBroad's sales team') and names the concrete outcome ('get a link to pick a time for the intro call'), plus an equivalence anchor ('the same form as madbroad.co/book-meeting'). An agent can tell exactly what this does and what it produces, and none of the siblings (list_case_studies, get_role, apply_video_editor, etc.) overlap.

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 constraint 'Only use details the person has provided' is a real usage rule, implying this should only be invoked with user-supplied contact info rather than inferred data. However, there is no explicit statement of when to invoke it (e.g., only after the brand expresses interest in street interviews) and no named alternative or when-not condition.

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