AI Success Story

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

With no annotations, the description adequately discloses key behaviors: commits via GitHub API, triggers Heroku auto-deployment, and returns commit SHA. It could be improved by noting potential failure modes or prerequisites.

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: two sentences covering admin access, action, mechanism, side effect, and return value. 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?

Covers main behavior and return value, but lacks parameter descriptions and error/state details (e.g., submission must be pending, admin token validation). Given no output schema or annotations, more context is expected.

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 description does not explain the purpose or format of admin_token or submission_id. With 0% schema description coverage, this is a significant gap; the agent must infer their roles from the tool's purpose alone.

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?

Description clearly states the tool promotes pending submissions to published articles by committing to a GitHub repo, using specific verbs and resources. It distinguishes from siblings like reject_pending and list_pending.

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 'Admin-only' qualifier provides clear guidance on who should use this tool. The context implies when to use it (approve submissions) vs alternatives like reject_pending, but does not explicitly state when not to use.

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?

Without annotations, the description carries the full burden. It discloses the behavioral guardrail where requesting certain parts forces inclusion of others, and observes that forced_parts/forced_parts_reason make this observable. This adds significant behavioral insight beyond 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?

The description is three sentences and front-loads the core purpose. While it is efficient, the guardrail explanation could be slightly more concise, but overall it earns its place.

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 no output schema, the description lacks explanation of the return format. It mentions forced_parts and forced_parts_reason but does not describe them. The schema covers inputs well, but the tool's output behavior is incomplete for an agent.

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 already has 100% description coverage for both parameters. The description adds extra semantics by explaining the interaction between parts and the forced companion behavior. This goes beyond the schema's individual descriptions.

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 retrieves a story by slug, either in full or a subset. The verb 'retrieve' and resource 'story' are specific, and it distinguishes from sibling tools like search_stories which search rather than fetch by exact slug.

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 on how to use the parts parameter with the atomic-context guardrail, explaining which parts force others. However, it does not explicitly state when to use this tool versus alternatives like search_stories, though it is implied by requiring a slug.

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?

Given no annotations, the description discloses auth requirement and ordering behavior. However, it omits details like pagination or empty result handling.

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 cover purpose, access, and ordering with no irrelevant content.

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 is provided; the description does not specify return structure or fields, leaving a gap for agents.

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 baseline is 3. The description reinforces the admin token's role but adds little beyond the schema's own 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 explicitly states 'List submissions awaiting curation' and restricts to 'Admin-only', clearly distinguishing from approve/reject siblings. It also notes 'Returns oldest-first', adding specificity.

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 indicates when to use (admin context) via 'Admin-only' and 'Gated by the admin token', but does not explicitly mention when not to use or 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?

With no annotations, the description carries full burden. It discloses that the reason is recorded and surfaces to the submitter on poll. This adds valuable behavioral insight beyond a mere action statement. However, it does not mention whether the action is reversible or other side effects.

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 two concise sentences. The first sentence front-loads the core purpose and restriction. The second adds key behavioral detail. 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?

Given no output schema and 3 required params with no docs, the description is minimal. It tells the action and one behavioral aspect (reason appears on poll). But it lacks what the tool returns (e.g., success/failure, updates to status). For a simple admin action, it's minimally adequate but leaves gaps.

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?

Input schema has 0% coverage, so description must compensate. It only mentions that 'reason' is recorded, adding some meaning. But 'admin_token' and 'submission_id' are not explained. For a token meaning authentication and an ID meaning the target, the description should clarify, but does not.

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 'Drop a pending submission.' The verb 'drop' is specific, the resource is 'pending submission', and the sibling tool 'approve_pending' provides contrast, making the purpose 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?

Description explicitly marks as 'Admin-only', which guides usage context. It implies the tool is for pending submissions only (via the name and context). However, it does not explicitly state when not to use it or mention alternatives like 'approve_pending'.

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?

No annotations provided, so description carries full burden. It describes the search and ranking behavior ('Returns ranked matches with 'why_relevant' snippets') and implies a read-only operation through 'Consult prior incidents'. While not explicitly stating no side effects, it provides sufficient behavioral context for an agent.

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 well-structured and front-loaded with the core purpose. Each sentence adds value: purpose, corpus type, usage timing, output description, and follow-up. No waste; appropriate length for a search tool with specific guidance.

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 3 parameters, no output schema, and no annotations, the description is highly complete. It covers input semantics, usage context, output format, and even suggests a next step. All relevant aspects are addressed, making it easy for an agent to use 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%, so baseline is 3. The description adds meaning beyond the schema: it clarifies 'tags' as a 'soft boost', explains 'situation' as natural-language one-to-three sentences, and mentions default and max for 'limit'. This provides useful context for proper parameter usage.

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?

Clearly states 'Consult prior incidents' with a specific verb and resource. The description distinguishes the tool from siblings like 'fetch_story' and 'submit_story' by specifying the corpus (war-stories on deploy, debugging, etc.) and the context of use.

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?

Explicit guidance to use this tool 'BEFORE falling back on training' and to follow up with 'fetch_story'. It also explains why it's valuable (real incidents catch gotchas) and what kind of scenarios it covers, aiding the agent in deciding when to invoke it.

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?

Discloses that the pending queue is in-memory and wiped on dyno restart, leading to 'unknown' status, which is critical behavioral info beyond a simple read.

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 concise sentences with front-loaded purpose and critical behavioral context. No extraneous 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?

Covers return format and important state behavior (dyno restart) despite no output schema. Complete for a simple lookup 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?

Schema description coverage is 100% for the single parameter; the description adds no new parameter-specific info beyond what the schema provides.

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?

Clearly states verb 'look up' and resource 'submission by id'. Distinguishes from siblings as no other tool does a simple lookup by ID.

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?

Implies public read usage by starting with 'Public read', and provides context about dyno restart wiping the queue, but does not explicitly state when to use vs 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?

Despite no annotations, the description discloses the token's role (rate-limiting, not identity), body validation against a spec, immediate return status (queued/rejected), and suggests polling with submission_status. It could add more on error handling or invalid token behavior, but is fairly transparent.

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 two sentences, extremely concise. The first sentence states the action and token requirement; the second covers validation, return format, and polling. Every part adds value with no 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 output schema, the description adequately explains the return object (status, submission_id, errors) and suggests polling. It covers body format and frontmatter specs. It could be more complete on the errors array content, but overall sufficient for the tool's complexity.

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%, but the description adds meaningful context: token is out-of-band and rate-limiting only, body must follow format spec at /docs/format-spec, frontmatter constraints like title ≤70 chars, date format, etc. This goes beyond the schema's field descriptions.

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 that the tool submits a success-story article for human curation, using a specific verb and resource (submit story). It distinguishes from siblings like approve_pending, fetch_story, etc., which have different purposes (approval, retrieval, etc.).

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 explains the token requirement and that it is for rate-limiting only, not identity. It mentions the body format spec and required sections, guiding the agent on how to use the tool. It does not explicitly state when not to use it, but the context is clear.

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