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 the root requirement but omits details about behavior on invalid hash_id, file overwrite, or synchronization. Minimal transparency beyond the prerequisite.

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 core purpose, second states a crucial prerequisite. No wasted words, front-loaded with 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?

No output schema exists, so the description should explain return values or success/failure indicators. It also doesn't mention error handling or async behavior. For a file export tool, more context would be helpful.

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 documents parameters. The description adds context about root requirement, which is not in the schema. This adds value 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 verb 'export', the resource 'cached raw data', and the output format 'JSON or JSONL file'. It distinguishes from siblings like get-raw-data which retrieves data but does not export to file.

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 a key prerequisite: requires MCP client to provide roots. However, it does not explicitly state when not to use this tool or suggest alternatives, leaving some gap in 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 the 300-record limit and truncation message. No annotations provided, so description carries full burden; it effectively conveys read-only behavior without 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?

Two sentences with no redundancy: first states core function, second adds limit and guidance. 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?

Adequately covers input and behavior given the tool's simplicity and lack of output schema. Could mention return format, but limit detail compensates.

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 already describes hash_id fully; description adds value by directing users to the 'recent-queries' resource for valid IDs, enhancing parameter usability.

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 action (retrieve), resource (raw data from cache), and key identifier (hash ID). Distinguishes from sibling 'export-raw-data' which is about exporting.

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 hint to use 'recent-queries' resource for hash IDs, but does not explicitly state when to use this tool versus alternatives like export-raw-data.

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 key behaviors: requires date range, multiple episodes may occur, difference between plant and animal data, and -9999 indicates missing data. This covers important behavioral aspects 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 structured with clear headings (About, When to use, Key applications, etc.), but it is somewhat verbose. Some points in 'Key applications' overlap with 'When to use'. It could be more concise while retaining 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?

The tool has 17 parameters, no output schema, and is complex. The description covers usage, important considerations, and data interpretation, including mention of individual_id, onset/end dates, and duration. However, it lacks explicit details on result structure, pagination, or error handling, which is a gap for 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 coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the schema descriptions; it mentions high-level concepts like date range and bounding box but does not elaborate on parameter details. The 'Data interpretation' section mentions output fields but not parameter specifics.

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 provides start and end dates of phenological activity for individual plants and animal species, derived from status data. It specifies the resource (individual phenological episodes) and the verb (provides dates). However, it does not explicitly distinguish from siblings like site-phenometrics, so it misses some differentiation.

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 includes a 'When to use' section listing specific applications (e.g., studying phenological diversity, analyzing individual responses to microclimates). It provides clear context for intended use but does not explicitly state when not to use or mention alternative tools.

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 carry the full burden. It mentions that results show time-series data of phenological abundance aggregated by frequency, but does not disclose whether the tool is read-only, has authentication requirements, or causes side effects. Key behavioral traits like idempotency or data source limitations are absent.

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 quite long with multiple sections (about, when to use, key applications, scientific context, etc.). While well-structured and informative, it could be more concise. Approximately 200 words, which is acceptable but exceeds the typical length for a tool description.

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 large number of parameters (17) and no output schema, the description provides rich scientific context, data interpretation guidance, and example research questions. However, it lacks explicit details on the exact structure of the output (e.g., fields, pagination). This is a minor gap but still informative overall.

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?

All 17 parameters have descriptions in the schema (100% coverage). The description adds value by emphasizing the necessity of date range and frequency, recommending species and phenophase specification, and explaining the climate_data flag. It also provides context for how parameters relate to scientific use cases, going beyond the raw 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 identifies the tool as summarizing the intensity and abundance of phenological activity across multiple individuals, sites, or time periods. It explicitly distinguishes itself from siblings by focusing on 'how much' rather than 'when', and provides concrete examples like synchrony analysis and peak activity timing.

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 includes a 'When to use' section listing applications (e.g., species synchrony, climate change impacts), but does not specify when not to use this tool or mention alternative sibling tools. It gives clear context for use but lacks exclusions or direct comparisons.

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 does not disclose side effects, authentication needs, rate limits, or whether the tool modifies data. The only behavioral hint is that it constructs a map, but important traits like destruction or idempotency are missing.

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 single-sentence description is efficient and front-loaded with the core action. It wastes no words, but could benefit from a brief structure break (e.g., separating purpose from constraints) for readability.

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 lacks critical details: no output specification (e.g., image, URL), no mention that tool_name and plot_type are fixed (const), and no clarification on how the 'previous query' results are accessed. For a 4-param tool with no output schema, more completeness is 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?

Schema description coverage is 100%, providing baseline 3. The description adds context by mentioning longitude, latitude, and variables (though these are not in the schema), which suggests the tool uses data from a prior query. The schema already explains the parameters, so the description adds limited additional meaning.

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 constructs a map from a previous Site Phenometrics query using longitude, latitude, and variables to plot on a USA map. It distinguishes the tool from siblings by focusing on visualization rather than data retrieval. However, it does not specify what 'results' means (e.g., a data object or reference), which could cause minor ambiguity.

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 the tool must be used after a Site Phenometrics query but provides no explicit guidance on when to use this tool versus alternatives (e.g., export-raw-data, individual-phenometrics). No exclusions or conditions are stated, leaving the agent without clear decision-making context.

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 mentions the result is stored as a readable resource, which adds some context about persistence. However, it does not specify read-only nature or any side effects, beyond what is implied by 'retrieve'.

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, front-loaded sentence. However, it redundantly includes the endpoint URL, which could be omitted for conciseness.

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 tool (one parameter, no output schema), the description adequately covers the purpose, parameter, and result behavior (stored as resource). It does not explain what happens if the comment is missing, but that is a minor gap.

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 the baseline is 3. The description does not add extra meaning beyond the schema; it simply restates the parameter purpose.

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 retrieves the comment for a given observation, using a specific endpoint. This verb+resource structure distinguishes it from sibling tools like get-raw-data or individual-phenometrics.

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?

There is no guidance on when to use this tool versus alternatives. The description only states what the tool does, not when it is appropriate or when to avoid 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?

No annotations are provided, and the description does not disclose behavioral traits such as whether the tool is read-only, destructive, or requires authentication. The SQL query nature implies read access, but this is not explicitly stated.

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 overly long (listing all 70+ table headers) and not front-loaded effectively. While informative, it could summarize the table structure more concisely without sacrificing essential details.

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 single parameter and no output schema, the description adequately covers the table schema needed for querying. However, it lacks usage guidelines and behavioral transparency, which are important for complete context.

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?

While the schema already describes the 'sql_query' parameter, the description adds significant value by detailing the entire table structure (headers, rows, descriptions). This helps agents formulate precise queries, compensating for the minimal parameter description in 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 states 'Query an SQL database for structured summaries of studies' which clearly indicates the tool's function (querying literature data). It distinguishes from siblings like 'get-raw-data' which focus on raw observation data. However, it could be more specific about the type of literature (e.g., phenology studies).

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 no guidance on when to use this tool versus alternatives like 'export-raw-data' or 'observation-comment'. It does not specify when not to use it or mention any prerequisites.

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 behavioral traits. It does not state whether the tool is read-only, required permissions, rate limits, or side effects. The table descriptions hint at a non-destructive query, but it is not explicit.

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 lengthy due to detailed table schemas, which are necessary for writing SQL but could be summarized. The purpose is stated upfront, but the overall structure could be more concise.

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 should explain return format and error handling. It lists table headers but does not specify how results are returned or any limitations. For a single-parameter tool, this leaves gaps 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?

Schema coverage is 100% for the single 'sql_query' parameter, so baseline is 3. The description provides table structures that aid in formulating queries, adding practical value beyond the schema's generic description, but does not enhance parameter semantics directly.

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 the tool queries an SQL database for reference material to translate natural language into specific IDs and terms for other NPN API tools. It clearly distinguishes itself from sibling tools focused on raw data or phenometrics.

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 advises against querying the 'datasets' table unless specific observer groups are mentioned, providing direct usage guidance. It implies use before other tools but does not explicitly contrast with siblings or 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?

The description discloses that the tool averages individual data, uses -9999 for missing values, and specifies site size. While no annotations are provided, the description covers key behavioral aspects, though it could explicitly state the tool is read-only.

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 clear sections and front-loaded with the tool's purpose. While it is lengthy, each section adds value by providing examples and applications. It is concise for the amount of information conveyed.

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 has 17 parameters and no output schema, the description provides sufficient context on purpose, usage, and data interpretation. It explains averaging and missing values, though it could benefit from describing the output format.

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 baseline is 3. The description does not add significant parameter-level details beyond the schema, but it provides overall context. This is adequate given the schema covers all parameters.

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 aggregates individual phenological data to provide average start and end dates for each species at each monitoring site. It distinguishes itself from sibling tools like 'individual-phenometrics' by emphasizing the averaging across individuals.

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 includes a 'When to use' section listing several applications and examples, providing clear context for usage. However, it does not explicitly mention when not to use the tool or compare it with 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?

No annotations provided, so the description carries full burden. It explains raw data nature, missing values (-9999), and includes a performance warning about massive datasets. Could explicitly state read-only nature but is comprehensive.

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 sections for clarity, but somewhat lengthy. Every section adds value; could be slightly more concise but effective.

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 complex tool with 16 parameters and no output schema, the description covers purpose, usage, performance, and data interpretation comprehensively. Lacks specific output format details but 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?

Schema coverage is 100% with clear parameter descriptions. The description adds context by recommending small date ranges and bounding box filtering to prevent crashes, enhancing parameter understanding 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?

The description clearly specifies that the tool retrieves raw, unprocessed observation records with phenological status and intensity. It contrasts with aggregated sibling tools like Individual Phenometrics, making the purpose distinct.

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 'When to use' and 'When not to use' sections with named alternatives (Individual/Site/Magnitude Phenometrics). Provides concrete applications like data validation and custom aggregations.

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