787daily

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

Discloses no outside knowledge used, refusal mechanism, and return shape ({answer, sources, refused}). No annotations exist so description carries full burden and does well.

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 states purpose and output, second adds usage and sibling distinction. 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 simple Q&A nature, 100% schema coverage, and no output schema, description fully covers operation, limits, and output. Complete for agent decision-making.

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%. Description adds meaning: explains question scope and optional filter, and that answer is synthesized from corpus. Slight deduction for not adding specific examples or parameter format.

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 answers questions about Puerto Rico using the news corpus, providing grounded cited answers. It distinguishes from raw article search with sibling tool search_news.

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 says when to use (for synthesized answers) and when not (off-topic or raw matches → use search_news). Also mentions refusal for off-topic queries.

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. The description discloses newset-first ordering, case-insensitive canonical name matching, and return format, but lacks details on pagination, error handling, or limits.

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, no wasted words. Information is front-loaded and well-structured.

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?

Tool is simple with one parameter. Description covers purpose, behavior, and return format. Lacks details on empty results or limits, but adequate for a straightforward 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%, so baseline is 3. The description adds value by clarifying case-insensitivity and canonical name matching, exceeding basic schema info.

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 returns articles mentioning a specific named entity, with details on matching and return structure. It distinguishes from siblings like get_by_municipality and keyword_search_news.

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 usage for finding articles about entities but does not explicitly state when to use or not use this tool compared to siblings. No exclusions or alternatives are mentioned.

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 partially discloses behavior: it returns articles matching a municipality, sorted newest-first, and gives output shape. However, it does not clarify matching semantics (e.g., exact match, case sensitivity) or disclose potential auth or rate limits.

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, three sentences long, and front-loaded with the primary purpose. Every sentence is relevant and without 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 no output schema, the description explains the return format (name, count, articles[]). However, it does not specify the inner structure of articles, nor does it mention error cases or pagination, leaving some gaps for a tool with a single parameter.

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 describes the 'name' parameter as a 'Municipality name'. The description adds value by noting it accepts canonical names and common variants, which enhances understanding 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 clearly states the tool returns articles mentioning a specific Puerto Rico municipality, with newest-first ordering. It distinguishes from sibling tools like search_news or get_by_entity by specifying the municipality filter.

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 examples of valid inputs ('San Juan', 'Ponce', 'Rincón') but lacks explicit guidance on when to use this tool versus alternatives like keyword_search_news or search_pr_news. No when-not-to-use or alternative references.

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 states it's live conditions from public data, implying read-only, but lacks details on authentication, rate limits, or return format. Could be more transparent but adequate for 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 sentences, front-loaded with key information. No redundant words. Efficient and structured effectively.

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 one parameter, no output schema, and no annotations, the description adequately covers what the tool does and how to use it. Could mention units or data freshness, 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?

Schema coverage is 100% with description for spot parameter. The description adds value by directing users to list_condition_spots for valid keys, supplementing the schema example.

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 live conditions for a Puerto Rico spot, listing specific data types (wave height/period/direction, sea temp, air temp, wind). It distinguishes from siblings like list_condition_spots for valid keys.

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 tells the user to use list_condition_spots for valid keys, providing clear context for when to use that sibling. Does not explicitly state when not to use this tool, but the context is sufficient.

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 burden. It discloses that estimates are vintage-labeled and that suppressed small-town estimates are null, which helps the agent understand potential null returns. It does not cover idempotency or authentication, but for a read-only data tool this is adequate.

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, dense sentence but conveys all necessary information without redundancy. It is front-loaded with the tool's purpose and packs metrics, scope, and caveats efficiently.

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 explains the return types (median gross rent, median household income, median home value) and geographies. With only one optional parameter and simple schema, the description is nearly complete, though it could mention that output is numeric values.

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 describes 'town' as optional with a brief description. The description adds value by explaining the behavior when omitted (island+US+all towns) and by providing examples of formats (name or slug, e.g., 'Ponce' or 'san-juan'), going beyond the schema's minimal 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 clearly states the tool provides Puerto Rico cost-of-living figures from U.S. Census ACS 5-Year Estimates, listing specific metrics (median gross rent, household income, home value) and geographic scope (island, US, municipios). It distinguishes itself from siblings which are about news, safety, and conditions.

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 clear guidance on when to omit the town parameter (for island + US summary) and when to include it (for a specific municipio). While it doesn't explicitly contrast with sibling tools, the context signals show siblings are unrelated, making usage 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?

No annotations are provided, so the description must disclose behavior. It states 'Returns summaries + links only,' which is transparent about output, but does not mention data freshness, authentication needs, or any side effects. Adequate but minimal for a read-only tool.

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, front-loaded with the tool's purpose, and every word adds value. No redundancy or unnecessary 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 low complexity (one optional parameter, no output schema), the description covers the main aspects: what it does, what it returns, and the source. Minor gap: no mention of ordering or that it's the latest stories only.

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 only parameter 'limit' has a schema description, and the tool description adds context about returning summaries and links. Since schema coverage is 100%, baseline is 3. The description does not add new semantic 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 clearly states it provides a daily briefing of Puerto Rico news in English, with links to Spanish sources. It uses a specific verb ('get') and resource ('daily briefing'), and distinguishes from siblings like search_pr_news and list_sections.

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 usage for getting a daily briefing but does not explicitly state when to use this tool versus alternatives like search_pr_news or list_condition_spots. No guidance on prerequisites or 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?

No annotations are provided, so the description carries the full burden. It discloses the data content and source, but does not mention any behavioral traits such as rate limits, authentication requirements, caching, or side effects. The tool appears to be read-only, but no explicit assurance is given.

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 long, front-loads the most important information (what the tool does and scope), and avoids unnecessary detail. Every sentence contributes meaning 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?

Given the tool's complexity (multiple statistics types) and lack of output schema, the description covers the key data points included. However, it could be more complete by mentioning update frequency or any limitations on data recency.

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 optional parameter 'town' is described in the schema with examples (e.g., 'Ponce' or 'san-juan') and states that omitting it returns an island summary with all 78 towns. The description adds context on the default behavior, enhancing the schema documentation.

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 provides Puerto Rico crime statistics from a specific source (PRPD Type I via Instituto de Estadísticas), including year-to-date totals, monthly homicide series, victim demographics, and per-municipio counts with rates. It distinguishes itself by focusing on safety stats and specifying the data source and type (reported incidents vs. surveys).

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 using this tool for Puerto Rico crime statistics but does not explicitly state when not to use it or mention alternative tools like get_by_municipality. No guidance on context or exclusions is provided, leaving the agent to infer appropriateness from the description alone.

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 implies a read-only operation by stating it returns results, but does not explicitly disclose the read-only nature, rate limits, authorization requirements, or what happens with no results. Adequate but lacks explicit safety guarantees.

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 clear, front-loaded sentences with no redundant information. Every word 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?

For a simple search tool with 3 parameters and no output schema, the description adequately covers the return format (summaries with links). It does not mention ordering or result defaults, but these are covered by the schema parameters. Minor gaps but largely complete.

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 schema already describes all parameters. The description adds minimal additional meaning beyond repeating that query searches title+summary and section filters. The baseline of 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's function: keyword search over a specific news archive by title/summary with optional section filtering, and specifies the output (summaries with links). It also distinguishes itself from the sibling 'search_news' by noting that sibling is for semantic/vector 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?

The description explicitly tells when to use this tool (keyword search) and when to use an alternative ('for semantic/vector search, use search_news'). This provides clear guidance for the agent.

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 that the verdict is based on buoy and marine data at the site's last build, implying a read-only operation. This is sufficient context for a listing tool.

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 the core purpose, and a secondary sentence for guidance. 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?

No output schema exists, but the description explains the response includes spots, activities, and a verdict. This is adequate for a 0-parameter list tool, though it could clarify ordering or pagination if needed.

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 no parameters, and the schema coverage is 100% (none needed). The description adds no parameter info, but baseline 4 is appropriate since no additional meaning is required.

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 specifies the verb 'List', the resource 'every 787daily Puerto Rico adventure spot', and includes details about activities and a verdict. It clearly distinguishes from sibling tools like get_conditions, which provides live numbers.

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 tells when to use get_conditions for live numbers, offering clear guidance on alternatives. However, it could mention more about when to use this tool relative to other listing tools, but the sibling tools are sufficiently distinct.

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 the description carries full burden. It only states the purpose without disclosing behaviors like caching, ordering, or safety guarantees. A read-only list tool is safe, but behavioral transparency is minimal.

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?

Single, concise sentence that is front-loaded and contains no waste. Every word 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?

For a simple list tool with no output schema or nested objects, the description fully covers what the tool does and what it returns (sections and their coverage).

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?

No parameters exist, so schema coverage is 100%. The description adds no parameter details, but baseline for 0 params is 4. No additional info needed.

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 787daily's news sections and what each covers, using a specific verb and resource. It distinguishes from siblings like get_conditions and search_pr_news, which focus on different content.

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 when needing to know available sections, but lacks explicit guidance on when not to use or alternatives. For a simple list tool, this is adequate.

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 that the tool does not generate an answer, which is a key behavioral trait. However, it does not mention read-only nature, authorization needs, rate limits, or other side effects. Given the absence of annotations, the description is minimally adequate 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?

The description is extremely concise, consisting of two sentences. The first sentence front-loads the core purpose, and the second provides usage guidance. No wasted words, every sentence 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 the complexity (2 params, no output schema), the description adequately covers what the tool does, what it returns (list fields), and when to use a key sibling. However, it does not differentiate from other search siblings (keyword_search_news, search_pr_news), which could be helpful for an agent. Still, the core functionality is well-explained.

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 value by clarifying the query is a 'free-text question or topic' and stating that topK defaults to 6 (not specified in schema). This provides additional context beyond the parameter names and types.

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 semantic vector search over a specific news corpus and returns article matches. It explicitly distinguishes from the sibling ask() by contrasting 'matching articles' vs 'synthesized answer', making the purpose clear and differentiating it from alternatives.

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 when to use this tool ('when you want matching articles rather than a synthesized answer') and when to use a specific alternative (ask()). However, it does not address other search siblings like keyword_search_news or search_pr_news, leaving some ambiguity about how to choose among them.

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 discloses that it searches over title and summary and allows section filtering, but does not mention result format, pagination, or side effects. Minimal behavioral context beyond what schema provides.

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 identifies legacy alias, second states function and key alternative. No superfluous words. 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?

Given simple read operation and 100% schema coverage, description covers purpose, usage, and alternative. Lacks output format details, but sufficient for basic search 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%, so baseline is 3. Description adds 'keyword search over title/summary' for query parameter, but section parameter is only described as 'optional', adding little meaning beyond 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?

Clearly states it is a legacy alias for keyword_search_news and performs keyword search over title/summary with optional section. Distinguishes from sibling search_news which uses semantic/vector 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?

Explicitly says to use search_news for semantic/vector search, guiding when to use this tool vs the alternative. Also identifies it as a legacy alias, implying preference for keyword_search_news.

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