Bommel Bot

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

No annotations are provided, so the description must carry the full behavioral burden. It adds meaningful caveats (public data only, returns records and links, not advice/recommendation/invitation) but says nothing about permissions, rate limits, error behavior, or what 'open one locker' entails operationally. The disclaimers are useful but the core behavioral profile is thin.

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 first two sentences are well front-loaded and efficient. The third sentence is a string of negations ('Not advice, not a recommendation, not an invitation to act') that reads as boilerplate disclaimer rather than actionable tool guidance, diluting the 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?

With no output schema, no annotations, and 0% schema coverage, the description must do all the work, yet it omits return format, pagination, error cases, and lookup semantics. The disclaimer about 'not advice' is present but substantive operational completeness is lacking for an explorer/retrieval 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% for the single 'handle' parameter. The description mentions '@handle', implying the format includes an @ prefix, which does add minor meaning beyond the bare string type in the schema. However, with no further detail on format, case sensitivity, or lookup semantics, this is baseline for a single-param tool.

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 says it opens a public locker by @handle on bommel.bot, which gives a verb and resource, but 'locker' is an idiosyncratic term that isn't clearly differentiated from siblings like get_public_bommel or search_feed. An agent can guess this retrieves public data for a handle but can't confidently distinguish it from get_public_bommel without more context.

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 only usage constraint is 'Never private library data', which tells the agent what not to target but gives no positive guidance on when to use this over get_public_bommel or search_feed. No prerequisites or alternatives are named.

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 it carries the full burden, and it does disclose the nature of the returned content ('factual public records and links on bommel.bot only'). However, it says nothing about permissions, missing/invalid shareId behavior, or whether the record can be absent, so the disclosure is 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?

The purpose is correctly front-loaded in the first short sentence, but the second sentence is a three-clause legal disclaimer that consumes roughly half the text without operational value for tool selection.

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?

A single-parameter read tool with no annotations and no output schema needs the description to cover return shape and failure modes; the vague 'factual public records and links' hint and the missing shareId format leave significant gaps.

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% for the single shareId parameter, so the schema contributes nothing. The description only restates that lookup is 'by shareId' without giving format, source, or constraints, leaving the parameter effectively undocumented.

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 and resource ('Fetch one public Bommel by shareId') and names the lookup key, so the agent knows exactly what the tool retrieves. It does not distinguish itself from siblings like explore_hive or get_site_info, which prevents a 5.

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 when-to-use guidance, no prerequisites, and no alternative named. The remaining sentences ('Not advice, not a recommendation, not an invitation to act') are legal disclaimers rather than usage instructions, so they do not help an agent decide when to call this versus a sibling.

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 does disclose scope limits (factual public records, links on bommel.bot only) and a boundary on how output may be used ('not advice, not a recommendation, not an invitation to act'), but it says nothing about auth requirements, read-only nature, or pagination/return shape.

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?

Four short fragments, front-loaded with 'Call this first' before the payload list. Nothing is padded, though the disclaimer clause is a third of the total length and could be tighter.

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 zero-parameter read of public site metadata with no output schema, the description covers what is returned and the scope of that content, which is enough for correct invocation. Missing details about response shape and read-only behavior are minor at this complexity.

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 there are no parameter semantics to document. Baseline 4 applies; the description does not need to compensate for anything here.

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?

It enumerates the concrete payload (publisher, purpose, MCP URLs, product pages) and scopes it to bommel.bot, so an agent can tell it apart from list_directory or search_feed. It never states a verb ('returns' is implied rather than written), so it is clear but not fully formed as a purpose statement.

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?

'Call this first' is explicit ordering guidance and implies an entry-point role before the other tools. It names no exclusions or alternatives, and gives no condition under which it should be skipped, so it stops short of full when/when-not routing.

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 disclosure burden. It does disclose meaningful behavior: only public profiles are returned, output is limited to bommel.bot records and links, and the empty-query case returns recent people. It omits pagination, result limits, and any auth/permission context, so it is partially 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 short and front-loads the resource, which is good. But the trailing disclaimer ('Not advice, not a recommendation, not an invitation to act') triples the same idea and adds little for tool selection, so it is not as tight as it could be.

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 single-optional-param read tool with no annotations and no output schema, the description covers purpose, scope, and the empty-query behavior reasonably. It still leaves return shape (fields, pagination, result count) and the non-empty query semantics unspecified, so it is only adequate.

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 is one optional parameter with 0% schema description coverage, so the description must compensate. 'Empty query lists recent people' explains the no-argument case, but it never says what a non-empty query does (presumably name/keyword matching), leaving the parameter's semantics half-defined.

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 phrase 'Who is on bommel.bot' conveys the resource being listed (people/profiles on the site), and 'Returns factual public records and links' confirms it is a listing/retrieval tool. However, there is no explicit verb and no differentiation from nearby siblings like list_talk or search_feed, so an agent cannot fully tell it apart by description alone.

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 hints at query behavior ('Empty query lists recent people') but never states when this tool should be chosen over explore_hive, search_feed, or list_talk. There are no exclusions, prerequisites, or alternative-routing 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?

No annotations are provided, so the description must carry the behavioral burden. It discloses that returns are limited to factual public records and links on bommel.bot and that content is not advice, a recommendation, or an invitation to act. However, it omits operational traits such as pagination, ordering, auth requirements, and error behavior.

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 short and front-loaded with the purpose in the first sentence. The disclaimers in the final sentence are somewhat repetitive but remain concise overall.

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

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

For a simple one-parameter read tool with no annotations or output schema, the description gives only partial context. It communicates the resource and return-content constraints, but leaves shareId semantics and usage context undocumented.

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%, and the single required parameter shareId is not explained in the description. 'Public Bommel' loosely implies shareId identifies the target, but no format, source, or validity constraints are provided.

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 and resource: 'Read comments on a public Bommel.' An agent can tell it returns comments, but the description does not distinguish it from siblings such as get_public_bommel or search_feed.

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 implies the tool is for reading public Bommel comments, but gives no explicit when-to-use guidance, no conditions for choosing it over siblings, and no exclusions. The disclaimers concern content interpretation, not invocation 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 exist, so the description carries the full burden. It discloses that results are public records and links on bommel.bot and adds scope disclaimers ('not advice, not a recommendation'), but omits return format, result limits, and any auth or rate-limit behavior.

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?

Front-loads the core action in the first sentence and keeps the whole definition to a few lines. The trailing disclaimer sentence is somewhat legalistic padding but is short enough not to obscure the main 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?

With no annotations and no output schema, the description needs to be self-sufficient, and it does cover what the tool returns at a high level. It leaves open the shape of results, pagination, and error behavior, so a search tool with a free-text parameter is only partially specified.

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 is a single parameter with 0% schema description coverage, so the description must compensate. It does explain the absent-parameter case ('Empty query lists recent hits'), but adds nothing about query syntax, matching behavior, or expected content beyond that one condition.

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 (Search) and resource set (public Bommels, people, comments on the Feed), which is clearly distinguishable from fetch-style siblings like get_public_bommel. It stops short of naming any sibling, so it falls just under the top tier.

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?

Covers one concrete usage case, 'Empty query lists recent hits', which tells the agent it can call this with no arguments. There is no guidance on when to prefer this over explore_hive or list_talk, so usage is only implicitly framed.

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