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

With no annotations, the description carries the full burden. It usefully discloses the return artifact (a URL) and the interactive-browser payoff, but says nothing about behavior for invalid accessions, default database handling, or that it is a safe read operation. Adequate but with clear gaps for an annotation-free 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 short sentences with zero filler, front-loaded with the verb and the returned artifact before the supplementary browser context. 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?

For a simple two-parameter URL builder with no output schema, the description states what is produced and both parameters are fully documented by the schema. Minor missing detail (invalid accession behavior, whether the URL is directly fetchable) keeps it short of a 5.

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 schema already documents both the enum-constrained database and the accession-or-'cart' value. The description's mention of 'a specific sequence or the cart' restates rather than extends the schema, giving no format or edge-case detail beyond it.

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?

States a specific verb and resource: 'Get the URL to view a specific sequence or the cart in the SILVA taxonomy browser.' An agent can tell this is a URL-construction tool, though it never names or contrasts with siblings like silva_sequence_detail or silva_search, which also deal with sequences.

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 second sentence ('provides interactive exploration of the taxonomic context of sequences') implies why an agent would want the URL, but there is no explicit when-to-use, when-not-to-use, or alternative tool named. Usage must be inferred from the tool's purpose.

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 disclosure burden, and it does state the return contents (database IDs, full names, available taxonomies). Since this is a parameterless enumeration tool with no mutation risk, there is little additional behavior to disclose; only caching or refresh semantics are left unstated.

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 action and resource, with the second sentence efficiently covering return values. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless, annotationless, output-schema-less discovery tool, the description supplies everything needed: what it returns and why (databases plus their taxonomy systems). Nothing essential to invocation is missing.

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 tool takes zero parameters, so the baseline of 4 applies. There is nothing in the schema to clarify, and the description adds no misleading parameter expectations.

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?

States a specific verb and resource ('List all available SILVA databases') plus the secondary payload (supported taxonomy classification systems). This clearly distinguishes it from siblings like silva_search or silva_browser, which operate on database contents rather than enumerating them.

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 intent is implied: call this to discover database IDs and taxonomies before invoking silva_search, silva_browser, or silva_sequence_detail. However, no explicit when-to-use statement or named alternative is given, so the agent must infer the discovery role from the sibling set.

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 the description carries the full burden. It does disclose the AND-combination rule and the returned fields, which is helpful, but says nothing about read-only/non-mutating nature, result limits, pagination defaults, or whether the default database is ssu-144.

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, front-loaded with purpose, then return shape, then the combining rule. The return-field enumeration is somewhat long but earns its place since there is no output schema.

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 and no annotations, the description carries return-value and semantics information and does so adequately. Remaining gaps are minor: pagination/limit behavior and the default database can be read from the schema, though an agent would benefit from a note about the two selectable databases.

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 schema already documents every parameter including enums and defaults. The description's only extra semantic content — AND logic — is already stated in the criteria schema description, so it adds little beyond baseline.

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 names a specific verb and resource ('Search the SILVA rRNA database') and enumerates searchable fields and the shape of the result. It's clear what the tool does, but it never distinguishes itself from siblings like silva_browser or silva_sequence_detail, so an agent must infer the boundary.

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?

Usage is only implied: the field list and AND-logic statement suggest 'use this to find sequences matching multiple attributes,' but there's no explicit when-to-use, when-not-to-use, or pointer to silva_browser/silva_sequence_detail for browsing or retrieving a single record.

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 shape of the return payload in useful detail, implying a read-only lookup, but never states read-only semantics, permissions, pagination, or rate limits. Adequate but with clear gaps for an unannotated 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 purpose and payoff, then the prerequisite. The first sentence is dense but every clause names real content; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter read tool with no output schema and no annotations, the description compensates well by enumerating the returned fields and the ID provenance. It omits any mention of the ssu/lsu database choice, but the schema handles that fully.

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 schema already documents both silvaId and the database enum/branches. The description only echoes the provenance note for silvaId and adds nothing about the database parameter, so baseline 3 applies.

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 gives a specific verb+resource ("Get detailed information about a specific SILVA sequence") and enumerates the content categories returned (taxonomy across SILVA/LPSN/GTDB, environment metadata, quality features, publications). It implicitly distinguishes itself from silva_search by requiring an ID obtained from search results, though it never names a sibling directly.

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?

It states the prerequisite clearly: the internal SILVA sequence ID must come from search results, which routes the agent through silva_search first. It gives no explicit when-not-to-use case or alternative for browsing/list tools, so it stops short of 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?

With no annotations, the description carries the full behavioral burden. It usefully discloses the asynchronous execution model and that a web URL is returned for viewing results, which is meaningful context beyond the schema. However, it omits job lifetime/expiry, error behavior, permissions, and how results are later retrieved, so the behavioral picture is incomplete.

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 tight sentences with no filler; the core action and the async/return behavior are front-loaded. Efficient and well-structured, though the final sentence could be marginally more informative.

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?

There is no output schema, so the description must cover return behavior – and it does, stating the job runs asynchronously and returns a web URL. For a 9-param submission tool this is nearly complete, with only result-retrieval mechanics left unspecified.

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 schema already documents all 9 parameters including defaults, enums, and ranges. The description adds no parameter-level detail (e.g., mismatch semantics or database choice tradeoffs), so the baseline 3 applies.

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?

States a specific verb and resource ('Submit a TestPrime job') plus the exact purpose (evaluate coverage and specificity of a primer pair against SILVA). It is clear what the tool does, though it does not explicitly distinguish itself from the sibling silva_testprobe (probe vs primer pair) – that differentiation is left to inference.

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 when to use it (evaluating a primer pair) and notes the async workflow and result URL, but gives no explicit when-not-to-use guidance or direct routing to silva_testprobe for probe-based evaluation. Usage is implied rather than stated.

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, and it does disclose two useful traits: the job runs asynchronously and results are retrieved via a returned web URL. It does not cover permissions, rate limits, whether submitted jobs can be cancelled, or how long results persist, so the behavioral picture is only partial.

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 front-loaded sentences with the core action stated first. The middle sentence about TestProbe 3.0 is mildly redundant with the opening claim, costing it the top score, but nothing is padded.

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 9-parameter, no-output-schema tool the description supplies the critical missing piece: that the call returns a job URL rather than results directly. It stops short of describing what the result view contains or job lifecycle, leaving a small gap for an async submission 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 100% with all nine parameters documented in the schema itself, including enums, ranges, and the IUPAC probe format. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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?

States a specific verb and resource: submit a TestProbe job that finds probe/primer sequence occurrences in SILVA. It is concrete about what the job does, but it never distinguishes itself from the near-twin sibling silva_testprime, which an agent would need to tell apart.

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 explicit when-to-use guidance and no mention of alternatives, even though silva_testprime is an obvious candidate for confusion. The only usage-like hint is that the returned URL should be used to view results, which is closer to behavior than to tool selection.

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