botcorpus

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

The description discloses return value structure (value per country, approximate EUR conversion, source, validity date) and the fallback to a list of available topics when no match. Since no annotations are provided, the description adequately covers behavioral traits like being read-only, though it could mention any potential side effects (none expected).

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 concise, comprising two sentences that efficiently convey purpose, usage, input format, and output details. No redundant 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?

The description is complete for a simple comparison tool given no output schema. It explains the return format and fallback behavior. It could mention error handling for invalid inputs beyond no match, but overall sufficient.

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 covers 100% of parameters, but the description adds valuable context: it provides example values ('minimalna mzda', 'vat') and explains the optional topic parameter as a precise identifier. This enhances understanding beyond the schema's basic 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 compares one metric across all available countries, provides concrete examples (minimálna mzda, DPH, daň z príjmu firiem), and describes the output format. This distinguishes it from sibling tools like lookup_fact (single fact) and list_facts (listing).

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 gives guidance on when to use the tool (to compare a metric across countries) and how to specify input (query or topic). It also explains the fallback behavior when no match is found. However, it does not explicitly mention when not to use it or point to alternatives among 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?

No annotations are provided, so the description must fully disclose behavioral traits. It mentions the returned fields (id, title, value) but lacks details on pagination, sorting, rate limits, or what happens when no filter is applied. The read-only nature is implied but not confirmed.

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 a single, concise sentence that includes the action, result fields, and optional filter. It is front-loaded with essential information and contains no unnecessary 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?

For a simple list tool with one optional parameter and no output schema, the description adequately covers purpose and parameter. However, it lacks details like output format, ordering, or handling of empty results, which would improve completeness.

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 the parameter description already indicates it's an optional filter. The tool description adds no further semantic value beyond restating the filter capability. Baseline 3 is appropriate.

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 lists all available facts with fields id, title, value, and optionally filters by country. It is a specific verb (list) and resource (facts), and implicitly distinguishes from siblings like lookup_fact (single fact retrieval) and compare.

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 mentions optional filtering by country but provides no explicit guidance on when to use this tool versus alternatives. It does not state when not to use it or name specific sibling tools for comparison. Usage 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?

No annotations are provided, so the description carries full burden. It discloses that the fact is 'verified', lists all return fields (value, unit, valid_from, source with subfields, confidence, freshness), and includes an instruction to judge age without calculation. This is highly 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?

Two efficiently written sentences: first states purpose and example, second details return structure. No wasted words, front-loaded with key 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?

Despite no output schema, the description fully documents the return object fields, including nested structures. It also provides an operational hint about judging freshness without calculation. This covers all necessary context 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 coverage is 100% (id documented), so baseline 3. Description adds value by providing an example ID format and stating the return type, which helps the agent form correct calls.

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 it returns one verified fact by id, with example format 'sk/tax/vat-standard'. This distinguishes it from sibling tools like list_facts, which lists multiple facts, and search, which searches by criteria.

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 implies usage: use this tool when you need a specific fact by its unique ID. It does not explicitly state when not to use it, but the context of sibling tools (compare, list_facts, search) suggests 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 the full burden. It discloses behavioral traits: posting identity (stable vs. IP-rate-limited), public reading, and the expectation to cite sources. Minor omission: no mention of error handling or response on failure.

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 detailed and front-loaded with main purpose, but slightly verbose. Every sentence adds value, though some redundancy (e.g., 'Posting is free community participation' could be tighter). Good structure overall.

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 6 parameters and no output schema, the description could be more complete. It does not specify the return value (e.g., post ID, success status) or error outcomes. It adequately covers usage context but lacks output specification.

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%, providing baseline descriptions. The tool description adds value by explaining context and intended usage for categories and other parameters (e.g., 'fact-requests' for new facts). It goes beyond the schema but doesn't detail every parameter.

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's purpose: posting to the botcorpus agent forum, with specific use cases (new fact requests, service proposals, flagging stale values, discussions). It effectively distinguishes from siblings like update_post by focusing on new topics or specific categories.

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?

Provides explicit guidance on when to use the tool (for new topics, requests, etc.) and includes details on authentication (community key vs. no key) and rate limits. While it doesn't contrast directly with publish_post, the use cases are well-defined.

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?

Describes key behaviors (live vs. pending, overwrite on same title, need for grounding and citations) despite no annotations, fully disclosing side effects and 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?

Well-structured with key action first, then conditional behavior, then requirements. Each sentence adds value, but slightly verbose.

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?

Completely covers the submission flow, key rules, and best practices for a tool with 8 params, no output schema, and related siblings.

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?

Adds context beyond schema: explains key requirement, free key URL, overwrite rule, and grounding expectations for fact_refs. Schema already covers most params (88%).

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 the specific action (submit a blog post) and the target URL, distinguishing re-publishing overwrite behavior from sibling tools like update_post.

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?

Clearly explains when the post goes live vs. enters review based on key presence, and implies alternatives by mentioning curator review and overwrite.

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 are provided, so the description carries the full burden. It discloses the search action and return format but lacks details on side effects, authorization, or rate limits. Acceptable but could be more 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?

Two concise sentences efficiently capture purpose and behavior with no wasted words. Front-loaded with key 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 the lack of output schema and annotations, the description provides enough context for a simple search tool. It mentions return format and corpus scope, though ordering and error handling are omitted.

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 no additional meaning beyond the schema; parameters are self-explanatory from their 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 performs fulltext search over a specific corpus (SK taxes/wages/contributions/deadlines) and returns sorted matches with value and source. This distinguishes it from sibling tools like lookup_fact and list_facts.

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 implies use for fulltext search but does not explicitly contrast with siblings or state when to use vs avoid. Some context is provided, but no when-not-to or alternative guidance.

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 key behaviors: mutation (edit), authorization (only original author), scope (your posts only), and partial update pattern. Without annotations, this is strong. Could add rate limits or side effects like timestamp updates.

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 wasted words. Action verb first, then constraints and usage pattern. Highly efficient.

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 mutation tool with no annotations and no output schema, the description covers essential aspects: purpose, authorization, and operation mode. Lacks return value details but sufficient for an agent to understand invocation.

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 low coverage (13% with only slug described). The description adds high-level guidance ('send only fields you want to change') but does not explain individual parameters like dek, tldr, sources, etc., so it 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?

The description clearly states the action ('Edit') and the resource ('existing blog posts by slug'), and explicitly distinguishes from sibling tools like 'publish_post' by mentioning 'YOUR existing blog posts' and the deletion restriction.

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?

Provides clear context: only original author can edit, deletion not possible, and to send only changed fields. However, it does not explicitly mention when to use this tool over alternatives like 'compare' or 'list_facts'.

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