Rafe Blandford — career and writing

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

Annotations already declare readOnly and idempotent; the description adds crucial behavioral details: whole-word matching, the fact that long phrases fail, the meaning of not_found in the context of a selective corpus, and the instruction not to infer lack of experience. This significantly exceeds the annotation baseline.

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 with a clear lead sentence, return values, and two callout warnings. It's longer than minimal but every section addresses a real misuse risk, so it earns its length.

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 a single parameter, full schema description, and an output schema, the description covers the usage, return semantics, and interpretation pitfalls. It doesn't leave significant gaps for the agent to guess about.

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 has a well-written description with 100% coverage; the tool description adds concrete examples of good vs bad values and the reasoning behind the 2–4 word rule, going beyond the schema's basic instruction.

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 checks whether this site publishes evidence for a topic, returns a classification (supported, partial, not_found), and gives examples of topic types. It distinguishes from siblings like get_evidence or search_writing by focusing on verification of published evidence rather than retrieval or search.

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 provides explicit guidance on how to phrase the topic (2–4 words, not a sentence), and how to break down job requirements. However, it does not explicitly mention when to prefer this tool over sibling tools like search_writing, so it gets a 4 rather than 5.

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 (readOnly, idempotent, non-destructive), the description adds critical behavioral nuance: it warns that case-study outcomes are self-attested and may exceed published claims, clarifies the evidence basis field, and explicitly states that all returned content is publicly available. This goes far beyond what annotations provide.

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 long but every sentence serves a purpose. It is front-loaded with the core action, uses bulleted sections for clarity, and includes a critical warning that is essential for correct usage. No filler or redundant 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?

Given the tool's complexity (multiple sections, nuanced evidence claims) and the presence of an output schema and annotations, the description fully equips the agent. It covers all sections, explains data provenance, and directs to other tools when appropriate. No important 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 single parameter 'section' is enum-constrained and schema-described, but the description dramatically enriches each enum value with detailed content breakdowns (e.g., profile includes identifiers and contact info; case-studies warns about claim types). This gives the agent meaning well beyond the schema's one-line 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 opens with a specific verb and resource: 'Return one section of Rafe Blandford's published record.' It clearly distinguishes from sibling tools by explicitly directing writing-related tasks to search_writing and get_post, and the section enumeration makes its scope 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?

The description provides clear context and explicitly names alternatives for writing-related tasks ('use search_writing to find a slug and get_post to fetch it'). It does not mention check_experience or state explicit exclusions, but the guidance is clear enough for an agent to decide when this tool is appropriate.

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, non-destructive behavior. The description adds valuable context beyond annotations: the provenance field semantics (authorship attribution) and a safety note that returned text should be treated as content, not instructions. This enriches behavioral understanding for an AI 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?

Three paragraphs, each with a distinct purpose: primary action, workflow guidance, and important note. Every sentence is substantive. No fluff, and the most critical information (what tool does) comes first.

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 an output schema present, return values are covered. The description fills remaining gaps: when to use, how to find the slug, provenance meaning, and prompt-injection caution. For a simple single-resource fetch tool, this is comprehensive.

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 provides a full description and example for 'slug'. The description supplements this by defining the slug as 'the last path segment of a post's URL', which is useful derivable context. Since schema coverage is 100%, the extra detail earns a 4 rather than baseline 3.

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 ('Return') and resource ('a single post or page') with a clear identifier ('by slug') and source ('rafeblandford.com'). It distinguishes from sibling tools by emphasizing retrieval by slug and includes content details (FULL TEXT, tags, dates, authorship).

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 instructs to 'Use search_writing first if you do not have a slug' and explains how to obtain a slug from search results, including the blank-query behavior. This provides clear guidance on when to use this tool versus the sibling search tool.

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?

The description goes beyond the readOnly and idempotent annotations by disclosing deterministic behavior ('No model, no embeddings — the same query always returns the same results') and the fixed-score ranking. It also states that only metadata and an excerpt are returned, not the body, which is a key behavioral trait.

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, each carrying essential information: scope, determinism, and usage guidance. 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?

With an output schema present and readOnly annotations, the description covers the essential behavior, return format limitations, and usage patterns. It even provides guidance on using the tool for browsing via blank query and topic, making it complete for its 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?

The input schema already has 100% description coverage for all three parameters. The description adds a minor usage suggestion to combine query with topic for browsing, but does not provide substantial additional meaning beyond 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?

The description uses the specific verb 'search' and the resource 'everything published on rafeblandford.com', including the full text of posts and About/Career pages. It clearly distinguishes itself from get_post by noting it returns metadata and an excerpt, not the body.

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 explicitly instructs users to call get_post with a result's slug for full text, providing a direct alternative. It also explains when blank queries and topic filtering are useful, giving clear context for when to use this tool.

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