ZeroCrew directory

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description then adds genuine behavioral context the agent would otherwise need an output schema for: the payload includes reviews with maker replies, aggregate ratings, MCP server address, and up to 4 same-role alternatives. Minor gaps: no statement about what happens if the slug doesn't match, and the 'up to 4' cap is the only boundedness disclosed.

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-loaded with the action and key, with no preamble or filler. The return-value enumeration is long and reads as one dense run-on sentence, which hurts scannability, but each listed field informs the decision to call.

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 carries the full burden of explaining return content and does so thoroughly for a single-parameter read tool. What's missing is small but real: no mention of failure behavior for an unknown slug or of data freshness.

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 schema already gives the pattern and an example, so baseline would be 3. The description adds real provenance for the single parameter — the slug originates from search_tools or list_job — which is meaning not present in the 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?

States a specific verb and resource (get one tool's public page) plus the source directory and the exact lookup key (slug). It names the siblings search_tools and list_job as the place the slug comes from, so an agent can distinguish it from those without opening a 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?

The phrase 'by its slug (from search_tools or list_job)' routes the agent: search/list first, then fetch details here. However, it never states the inverse condition — e.g., that search_tools should be used when you don't yet have a slug — so the exclusion is implied rather than explicit.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavior: default A-Z ordering, that ZeroCrew does not rank results, that the response echoes which sort order was used, and a hard cap of 50 results. The 50-result cap is stated without saying how to page past it, which is the main remaining 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?

Front-loaded with the purpose, then ordering, then the limit, then the sibling pointer — a sensible order with little waste. The 'ZeroCrew doesn't rank them' sentence is slightly redundant with the sort explanation that follows.

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?

There is no output schema, so the description carries the return-value burden, and it does state result count limits and that the chosen order is echoed. It is nearly complete for a simple filtered list, falling short only on what happens when more than 50 tools exist.

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 earns more: it explains what must_use and using_now actually mean (counts of developers rating a tool a must-use or using it now) rather than just restating the enum, and it supplies example role/job values.

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 first clause names a specific verb and resource (list the tools for one job) and scopes it to the ZeroCrew directory with a concrete example. It also distinguishes itself from list_roles, which is named as the tool for browsing every role and job.

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 a clear usage context (need the tools for one role+job) and routes role/job discovery to list_roles. It explains when to pick each sort mode. It doesn't explicitly exclude search_tools or get_tool, so the sibling boundary is only partially drawn.

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 it as read-only, idempotent, non-destructive, and closed-world. The description adds useful behavioral context by explaining that it returns role/job hierarchy, live tool counts, and page URLs, going beyond the annotation 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 front-loaded with the core action and returned content, followed by a concise usage sentence. Every phrase adds information 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?

With no input parameters, no output schema, and rich annotations, the description supplies the missing return-value context: what is listed, the hierarchy, tool counts, and page URLs. That is sufficient for an agent to understand and call 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?

There are zero parameters, so the baseline is 4. The description does not need to explain parameter semantics beyond what the empty input schema already communicates.

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 ('List') and clearly names the resource: roles in the ZeroCrew directory, jobs within each role, live tool counts, and zerocrew.ai pages. It distinguishes itself from siblings by positioning its output as slugs for search_tools and list_job.

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 use cases: seeing what the directory covers or finding role/job slugs for search_tools and list_job. It does not explicitly state when not to use it, but the intended contexts are clear.

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 read-only, idempotent, closed-world behavior, so the bar is lower. The description adds real value beyond them: it explains the matching fields (name, maker, description, role, job), the 20-result cap, best-match ordering, and that each hit includes its zerocrew.ai page.

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?

Four short sentences, front-loaded with the purpose, then usage, then return shape, then narrowing and follow-up. No filler and no repetition of schema detail beyond what adds meaning.

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?

There is no output schema, and the description compensates by describing result count, ordering, and per-result content. With 6 parameters, 1 required, all documented, and the field-matching behavior explained, nothing needed 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining that the query is matched against name, maker, description, role, and job, and it groups the narrowing filters (role, job, kind, mcp) into a coherent usage note.

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 ('Search the ZeroCrew directory of AI agents, apps, and models') and describes what is matched against the query. It also explicitly routes to the sibling get_tool for full detail, so an agent can distinguish it from list_roles/list_job.

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 concrete when-to-use examples ('customer interviews', 'ai receptionist', 'bookkeeping') and names the follow-up alternative get_tool. It stops short of stating when not to use it or when to prefer list_roles/list_job, but the guidance is clear in context.

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