benmilne.com content

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds beyond: specifies exact returned fields (title, date, author, content_html, categories, tags), which is useful behavioral context. No contradictions.

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, front-loaded with purpose, no redundant words. Every sentence contributes essential 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?

Given high schema coverage and no output schema, description sufficiently covers how to identify the post, what fields are returned, and how to chain with siblings. No missing critical aspects.

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%, so parameters are already documented. Description adds value by explaining the id=0 special case and suggesting slug as alternative, beyond schema definitions.

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 retrieves a single post by id or slug, distinguishes from siblings (list_posts, search_posts) by focusing on a single resource, and includes the special id=0 case for book metadata.

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 slug from search_posts or list_posts results to chain calls, providing clear context. Does not explicitly state when not to use, but the purpose is sufficiently contrasted with siblings.

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 indicate readOnly and idempotent. Description adds that it returns 'summaries with title, date, URL, and excerpt' and only published posts, and supports pagination. No contradictions.

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: first covers purpose and return fields, second gives usage context and examples. No fluff, front-loaded key info.

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 read-only list tool with 4 parameters (all documented), annotations, and sibling tools, description covers browsing, filtering, pagination, and return fields. Minor gap: no default sort order, but not essential.

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 has 100% description coverage, so baseline is 3. Description repeats filter by category/tag and adds example category slugs. No additional parameter details beyond schema, but examples add slight value.

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+resource: 'Browse, filter, and paginate all published posts.' Distinguishes from siblings (get_post, search_posts) by focusing on browsing/filtering vs. single post or full-text 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?

Explicit telling when to use: 'Use when a user wants to browse topics, see recent essays, or find posts in a specific category or tag.' Provides example categories. Could be more explicit about when not to use or when search_posts is better, but sibling names imply 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?

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already indicate safe read behavior. The description adds that it searches only published posts, returns results ranked by relevance, and includes specific fields (title, date, URL, excerpt), providing useful context beyond the structured metadata.

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 concise sentences: first states the core action, second gives usage guidance with examples, third describes the output. Every sentence serves a purpose, no 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?

Given the simple schema (one parameter, no output schema) and annotations indicating read-only idempotent behavior, the description is quite complete. It explains the search scope, ranking, and return fields. It lacks details on pagination or result limits, but for a basic search this is acceptable.

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 defines query as a generic 'Search query string'. The description enriches this by stating it accepts keywords or phrases, and provides example topics (stablecoin infrastructure, payment regulation), helping the agent understand appropriate 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?

The description clearly states the tool searches all published posts by keyword or phrase, specifying the resource (posts) and the action (search). It differentiates from siblings like get_post (single post retrieval) and list_posts (listing all) by focusing on keyword-based retrieval.

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 advises using the tool when a user asks about a specific topic, giving concrete examples. While it doesn't explicitly state when not to use it, the context implies that for getting a single post or listing all, siblings should be used.

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