ListDrop

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

Goes well beyond the annotations by disclosing unowned-list deletion after 30 days, the secret claim URL behavior, OAuth lists:write requirements, URL-in-item linkification, view-only sharing via allowed_emails, and self-archiving via expires_in_days. These are material behavioral traits the annotations alone cannot convey, and nothing contradicts readOnlyHint=false or destructiveHint=false.

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 long but each sentence earns its place: it front-loads the core purpose and applicability, then covers account branches and optional-field behavior. The examples clarify 'list-shaped' without becoming 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?

Despite having no output schema, the description explains both output variants (claim URL vs account URL) and downstream behaviors like deletion, archiving, and sharing. Given the tool's complexity and sparse schema, the description is nearly complete for correct invocation.

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 real semantics for items (URL becomes a titled linked item) and for allowed_emails and expires_in_days. However, schema description coverage is only 29%, and the description does not explain tags, emoji, or description, so it only partially compensates for the sparse 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?

States a specific verb ('Saves'), a resource ('ListDrop list'), and a clear scope ('list-shaped content') with concrete examples. It is easily distinguishable from siblings get_list, my_lists, and send_feedback, which read lists or send feedback instead of creating.

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 defines when to use the tool: when the user wants a list that outlives the conversation. It also lists exclusions ('throwaway answers, secrets or sensitive data... content that isn't list-shaped') and distinguishes the two account-state branches, giving the agent clear routing conditions.

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?

Annotations already declare readOnlyHint=true, so the description is not required to restate that. It adds valuable behavioral context: the return format (markdown with title, items, notes, links), the accepted input forms (URL pattern or bare id), and the strict privacy constraint. No contradictions with annotations.

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, well-structured sentence that front-loads the core action and resource, then adds the input format and a key constraint. Every word earns its place; there is no fluff or repetition.

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-parameter read tool with no output schema, the description fully covers what the tool returns, how to specify the input, and the privacy limitation. Annotations cover the read-only nature, so nothing an agent needs to correctly call this tool 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?

Schema coverage is 100% with the param description 'List URL or id', but the tool description enriches this by specifying the exact URL format (https://www.listdrop.co/l/<id>/…) and explicitly confirming that a bare id is accepted. This goes beyond the schema and leaves no ambiguity about how to construct the parameter.

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 clear verb ('Returns') and a specific resource ('PUBLIC ListDrop list as markdown'), and specifies the input format (URL or bare id). It also distinguishes itself from siblings by explicitly limiting to public lists, while create_list and my_lists clearly cover other operations.

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 clearly indicates when to use this tool (for public lists) and explicitly excludes private lists with 'Private lists are never readable.' While it doesn't name the alternative for private lists (my_lists is implied), the exclusion is explicit enough for an agent to infer the correct usage boundary.

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?

Annotations already declare readOnlyHint=true, so the description doesn't need to restate safety. It adds valuable behavioral context beyond annotations: OAuth authentication requirements, the lists:read scope, private-list inclusion, and the 401 response when no account is connected. This is meaningful disclosure for an API-facing 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, no filler. The first sentence states the primary purpose and return contents; the second covers authentication and error behavior. All information is relevant and front-loaded.

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 parameters and no output schema, the description still gives the agent enough to call the tool correctly: what it returns, whether private items are included, the required auth scope, and the failure mode. Nothing essential is missing for selecting or invoking it.

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 has zero parameters and schema coverage is 100%, so there is no parameter information needed. The description adds no parameter details, but none are required. Baseline 4 applies for zero-parameter tools.

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 uses a specific verb ('Returns') and identifies the exact resource ('the connected user's own lists'), including the concrete fields returned (titles, visibility, item counts, URLs). It also clarifies scope by noting private lists are included, which distinguishes it from a generic list-all tool and from siblings like get_list that target a single list.

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 clearly indicates when to use this tool: when the connected user wants their own lists, including private ones. It also states the prerequisite (connected ListDrop account with lists:read scope) and the failure signal (401). It does not explicitly name alternatives or exclusion conditions, but the context is clear enough for an agent.

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

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

Annotations only say the tool is not read-only, not idempotent, and not destructive. The description adds valuable behavioral context: a person reads every message, no account is needed, and the message must exclude claim URLs, tokens, and personal data. It also clarifies when the email field is appropriate.

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 sentences with no filler: purpose, human-reading note, data safety rule, and email guidance. Every sentence earns its place and the most important trigger information is front-loaded.

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 feedback-sending tool with no output schema, the key context is prerequisites, payload rules, and when to include the optional email. All of these are covered explicitly. An agent has everything needed to invoke this 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema, especially for the email field and message content constraints. The 'kind' enum is self-explanatory in the schema, so no additional description is required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Sends a message to the ListDrop team') and gives explicit trigger conditions: report a problem, request a feature, or give feedback. This clearly distinguishes it from the list-management sibling tools.

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 clearly states when to use the tool with concrete user-intent examples. It does not name alternatives or exclusions, but the siblings are so different in purpose that confusion is unlikely.

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