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

With no annotations, the description should disclose behavioral traits. It only states conversion and parameter basics, missing details like whether the operation is read-only, performance implications, or error handling.

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 efficient: one sentence for the action, then parameter descriptions. No fluff, well-structured with front-loaded purpose.

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?

Output schema is present, so return values are covered. Parameter descriptions are adequate for basic usage. Missing context about typical use cases or output format, but acceptable for a conversion 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 0%, and the description provides brief explanations for both parameters (jsonl_path as file path, fields as optional list). This adds meaning but lacks finer details like allowed values or formatting.

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 ('Convert'), the resource ('genome JSONL data report'), and the output format ('TSV'). It distinguishes from sibling tools, which focus on downloading or summarizing, not conversion.

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?

No explicit guidance on when to use this tool versus alternatives like genome_summary_by_accession. The description implies usage after downloading a package but does not provide exclusions or when-not-to-use 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 provided, so description carries full burden. Describes behavior: checks installation, auto-installs if missing. Mentions return values (status, paths, version). Could mention potential side effects like system modifications or internet requirement, but overall sufficient.

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, concise and front-loaded with the main action. Every sentence adds value: action, usage guidance, return information. No waste.

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 zero parameters and a clear return description, the tool definition is complete. Output schema exists (though not shown) to detail return types. Description covers all needed information for an agent to invoke correctly.

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 (0 params). Baseline score of 4 per instructions. Description adds no parameter info, but none is 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's purpose: checking and installing NCBI CLI tools. It specifies the action (check/install), the resource (NCBI datasets/dataformat CLI), and distinguishes it from sibling tools which are all about data operations, not installation.

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 states when to use: 'Call this tool once before using any download or format-conversion tools.' Provides clear context of being a prerequisite. Lacks explicit 'when not to use' statements but not needed given the specificity.

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?

Without annotations, the description discloses key behaviors: returns local path, dehydrated packages need rehydration. It does not mention authentication or rate limits, but covers the main functional traits adequately.

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 front-loaded with the main verb and result, then details in a structured Args section. It is efficient but the Args block could be slightly more streamlined without losing clarity.

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 and the presence of an output schema, the description covers all necessary aspects: input parameters, output location, and the dehydrated workflow. It is fully complete for an agent to invoke correctly.

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?

With 0% schema coverage, the description fully explains each parameter: accessions format, include data types with defaults, output_dir fallback, and dehydrated's purpose. This adds critical 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 downloads a genome data package for assembly accessions and returns the local path. It differentiates from siblings like genome_download_by_taxon and genome_summary_by_accession through its specific verb 'download' and resource 'genome data package'.

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 parameter explanations with defaults and notes the dehydrated option's follow-up tool. It implicitly guides usage but lacks explicit when-to-use vs sibling tools, which would make it a 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?

No annotations are provided, so the description carries the full burden. It explains the dehydrated option and parameter purposes, but does not disclose that the tool writes files to the output directory, any potential side effects, or success/failure responses. The behavior is partially transparent but missing details about file creation.

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 with an introductory sentence, a usage tip, and a well-structured Args list. No unnecessary words; every sentence adds value.

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 downloads files and has an output schema (not shown), the description covers the main purpose and all parameters adequately. It could mention that the download creates files in the output directory, but it is reasonably complete for a download 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?

The schema has 0% description coverage, so the description must add meaning. It includes an Args section explaining each parameter beyond the schema: taxon (name or ID), include (data types list), output_dir (directory), dehydrated (recommended for large taxa), reference_only (only reference/representative). This provides excellent semantic detail.

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 downloads genome data packages for assemblies matching a taxon, specifying the verb 'download', the resource 'genome data packages', and the condition 'for assemblies matching a taxon'. It differentiates from siblings by mentioning the dehydrated workflow and referencing rehydrate_genome_package.

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 explicit guidance for large taxa (use dehydrated=True then rehydrate_genome_package). It does not explicitly compare to genome_download_by_accession, but the different purpose is inferred. The recommendation for dehydrated packages is clear and actionable.

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 being read-only, idempotent, or any side effects. For a retrieval tool, this is a significant gap.

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 short paragraphs, no unnecessary words. The description is efficient and front-loaded with the core purpose.

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?

Adequate but lacks mention of potential limits (e.g., maximum number of accessions) or pagination. With an output schema present, return value explanation is not 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?

The description adds value by specifying that accessions are 'RefSeq or GenBank assembly accessions' and provides examples. With 0% schema coverage, this compensates well, though it could be more explicit about format constraints.

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 'retrieve' and the resource 'genome assembly metadata' for 'NCBI accessions', distinguishing it from siblings like genome_download_by_accession or genome_summary_by_taxon.

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?

No guidance on when to use this tool versus alternatives. It does not specify when not to use or provide context for selection among sibling 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 carries full burden. It states that it returns assembly metadata but does not explicitly confirm it is a read-only operation, mention authentication needs, or rate limits. The search nature implies safety, but not fully 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 concise with a clear front-loaded purpose and a structured Args section. Every sentence adds value, though it could be slightly tighter without losing 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?

With 6 parameters (1 required) and an output schema, the description covers all inputs and states the return type (assembly metadata). It provides enough context for an AI agent to understand the tool's scope and usage.

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 0%, so description must add meaning. It includes an 'Args' section explaining each parameter with examples (e.g., 'human' for taxon) and possible values (e.g., 'chromosome' for assembly_level). The limit parameter notes server cap. This adds significant value beyond the schema defaults.

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 a specific verb ('Search') and resource ('NCBI genome assemblies') with clear matching criteria ('taxon name or tax ID'). It distinguishes from sibling tools like genome_summary_by_accession (different lookup method) and genome_download_by_taxon (download vs summary).

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 explains what the tool does but does not provide explicit guidance on when to use it versus alternatives like genome_summary_by_accession. No when-not-to-use or preference suggestions are given.

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 exist, so description carries full behavioral burden. It discloses behavior for both modes and error handling (unknown values return valid keys). No side effects or permissions needed for this read-only listing tool, so the description is sufficiently 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?

Description is concise with a clear structure: opening purpose, then mode-specific behavior, then parameter docs. Every sentence adds unique value, no fluff. Front-loaded with main idea.

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 the tool having an output schema (which need not be described), the description covers all needed context: purpose, usage modes, parameter semantics, and error behavior. Complete for a simple, single-parameter informational 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 only declares 'report_type' as optional string/null with 0% coverage. Description adds key semantics: it's a data report type key, provides examples ('genome-assembly', 'taxonomy'), explains effect of omitting or supplying it, and clarifies error handling. Fully compensates for missing schema 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 it describes data types NCBI Datasets can provide, explicitly listing examples (genes, genome assemblies, etc.) and noting it shows which other tools retrieve each type, distinguishing it clearly from siblings.

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 explains two usage modes: no arguments gives overview with tool mappings, optional report_type gives field categories and schema link. Also notes that unknown values return valid keys, providing complete when-to-use 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?

With no annotations, the description must disclose behavioral traits. It mentions that package_path can be a ZIP file or directory, but does not discuss errors, size implications, or side effects. The tool's read-write nature is not clarified.

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 with one functional sentence plus an argument definition. It front-loads the purpose but includes an 'Args:' section that is somewhat redundant with the schema. Still 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 simple tool with one parameter and an output schema, the description covers the essential: what it does and what input to provide. It does not elaborate on return values, but the output schema handles that. The context of sibling tools is understood.

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 description explains that package_path is a path to a dehydrated ZIP file or its extracted directory, adding significant meaning beyond the schema's plain string type. This is crucial given 0% schema description coverage.

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 fetches full sequence files for a dehydrated genome package, using the verb 'fetch' and specifying the resource. This distinguishes it from sibling tools that handle downloads by accession or taxon, data formatting, or summaries.

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?

No guidance is provided on when to use this tool versus alternatives, prerequisites (e.g., prior dehydration step), or exclusions. The description only states its basic function.

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?

Without annotations, the description should carry the burden of behavioral disclosure. It only says 'download,' implying a network operation, but does not mention file size, permissions, side effects, or whether the tool modifies any state.

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?

Very short, with the main action front-loaded. The parameter listing is concise, but could be more structured (e.g., bullet points) for clarity. 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 the presence of an output schema, the description does not explain return values or the nature of the download (e.g., file format, size). Sibling tools exist but no context is provided. Incomplete for a network-bound 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 description coverage is 0%, so the description must compensate. It adds basic meaning: 'taxon' is a name or NCBI ID, 'output_dir' is a directory. However, no details on formats, defaults, or constraints beyond what is 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 clearly states the tool downloads a taxonomy data package for a given taxon, which is a specific verb+resource. It distinguishes from sibling tools like genome_download_by_taxon, which downloads genome data, by specifying 'taxonomy' data package.

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?

No guidance on when to use this tool versus alternatives. For example, when to use taxonomy_download vs taxonomy_summary or genome_download_by_taxon is not explained. No mention of prerequisites or 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 full burden. It describes the output fields but does not disclose behavioral traits such as that it is a read-only operation, error handling for invalid taxon inputs, or any rate limits. The description is adequate but incomplete for full transparency.

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 a single sentence followed by a parameter explanation. The purpose is front-loaded, and every sentence adds value. 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 the tool has only one parameter and an output schema (not shown), the description provides sufficient context about the input and output. It lists the categories of returned data, which is helpful. Lacks details on error handling or edge cases, but the presence of an output schema reduces the burden. Nearly 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?

The input schema has 0% description coverage, but the description compensates thoroughly. It explains the parameter 'taxon' accepts both scientific names (with examples like 'human', 'Bacteria') and NCBI tax IDs, adding crucial semantic context beyond the schema's type definition.

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: 'Get taxonomy metadata for a taxon' and lists the types of data returned (lineage, rank, scientific name, common names, child taxa). It specifies the verb 'Get' and the resource 'taxon', making it distinct from siblings like 'taxonomy_download' which implies bulk data 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 implies usage for retrieving taxonomy metadata but does not explicitly state when to use this tool versus alternatives such as 'genome_summary_by_taxon' or 'taxonomy_download'. No guidelines for when not to use it are provided, relying on the agent to infer from the purpose.

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