Agger

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description doesn't need to repeat those. The description adds useful context by stating it confirms which login is active, which is a behavioral trait not fully covered by annotations. No contradictions exist.

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, compact sentence (three short segments) that conveys the essence and usage guidance. Every word adds value; there's no fluff. It is well-structured 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?

Given that the tool has no parameters and no output schema, the description provides enough context: it names the tool's output (e-mail of the broker) and its usage timing (before other operations). It could be slightly more complete by mentioning the format or that it returns no other data, but it is sufficient for a simple validation 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 tool has zero parameters, so the schema provides no parameter details. The description correctly does not invent parameters; it focuses on what the tool does. Since there are no parameters to explain, and the description clearly indicates the output (the e-mail of the connected account), a baseline of 4 is appropriate.

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: it shows the connected Agger account (broker's e-mail) and confirms which login is active. Although the name 'agger_list_accounts' is generic, the description adds specificity about what is listed (the connected account) and distinguishes it from other tools like 'authenticate' and 'connect' by focusing on validation of the active login.

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 explicitly says to use this tool to validate the connection before other operations, providing clear context for when to use it. It doesn't explicitly mention when not to use it or name alternative tools, but the context is reasonably clear given the sibling tools like 'authenticate' and 'connect' which likely handle initial setup.

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 idempotentHint=true and destructiveHint=false, so the safety profile is clear. The description adds that the token is a JWT and that session login expires, but it doesn't disclose what the tool returns or the exact behavior when called with no args vs with a token. It partially compensates but lacks some behavioral detail (e.g., does it validate the token, what is the output). No contradiction.

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 audience and purpose. Each clause adds value, and the formatting guides the agent on parameter usage. Zero 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 the tool's complexity (auth flow) and the minimal schema, the description covers the two usage modes, the token format, and the alternative permanent config. The sibling list shows no overlap, so no additional context is needed. 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?

Schema coverage is 0% since the description explains the token parameter's format (JWT) and its optionality, but the schema provides no description. The description adds meaning beyond the schema by detailing the two call patterns, which is helpful. It earns a solid 3 because it compensates for the schema deficit.

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 this tool authenticates an IDE agent by logging in via browser and obtaining an access token. It distinguishes itself from siblings by explicitly targeting IDE agents and explaining the two login flows (permanent config vs session-only).

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 when-to-use guidance: it tells the agent to guide the user to log in, offers two methods (config header permanent, or paste token session), and specifies calling with no args to get the link. It also mentions sibling tools like report_bug and show_version are unrelated to auth workflows.

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 establish readOnly, idempotent, and non-destructive behavior. The description adds useful conditional behavior: when all providers are connected it returns authenticated true and empty pending[], while missing credentials cause it to return a connect_url and per-install URLs. This is meaningful beyond the annotation fields.

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 two sentences long, front-loads the core purpose ('Returns connection status and URLs'), then provides necessary conditional detail. Every sentence adds value and there is no redundant or filler content.

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-only status tool with no output schema, the description covers the main expected behaviors: connected state, missing-credential state, and the useful URLs returned in each case. It is sufficiently complete for an agent to understand what the tool will do and what it will receive.

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, so there is no parameter documentation burden on the description. The baseline for zero-parameter tools is 4, and the description appropriately focuses on output and conditions instead.

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 starts with a specific verb and resource: 'Returns connection status and URLs.' It also clearly distinguishes itself from connection-establishing siblings like authenticate by indicating this is an inspection/read-only tool rather than a credential setup tool.

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 how the output changes depending on connection state, which implies the right time to call it (when checking current connection status or when credentials may be missing). However, it does not explicitly name alternatives or state when not to use connect versus authenticate or toolkit_info, so usage direction remains inferred rather than explicit.

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?

Adds substantial behavior beyond annotations: explains that invoke runs MCPs one-off without installation, returns connect/checkout links for auth/payment issues, flags installed status in search/describe, and requires owner/admin for write actions. No contradiction with annotations; openWorldHint is consistent with running external MCPs, and readOnlyHint=false aligns with mentioned write operations.

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 dense, with a logical flow: introduction, core workflow, key caveats, usage distinctions, prompt library, and permissions. Every sentence adds value, and the front-loaded purpose ensures immediate clarity. Despite its length, it remains efficiently organized for a tool with 14 actions and 23 parameters.

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 complexity, no output schema, and sparse annotations, the description is remarkably complete. It covers all actions, their use cases, permission requirements, edge cases (auth, wallet), and return behavior for key actions like describe, get_prompt, and publish_prompt. It fully equips an agent to use the tool across all its sub-functions.

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 compensates by explaining the meaning and usage of key parameters: action enum values, mcp_id, tool_id, prompt_* fields, and arguments. It does not cover every optional parameter (like limit, immediate, tier_slug), but the core semantics are clear enough for agents to select and invoke correctly.

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 is the official mcp.ai marketplace catalog and runtime, covering MCP discovery, description, invocation, and installation. It also includes a prompt library, distinguishing it from sibling tools like authenticate or connect. The purpose is specific and action-oriented.

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 explicit when-to-use guidance for each action: prefer invoke for occasional use, install only for permanent toolkit additions, list_tools for current callables, and explains subscribe/cancel, report_bug, and request_mcp. It also details the search→describe→invoke flow and auth/wallet retry procedures.

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 indicate idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds that the tool can be used for feedback and missing features, and mentions including conversation for reproduction. It does not contradict annotations, but it doesn't disclose additional behavioral traits like whether it creates a ticket or sends an email, which would be useful. Given annotations cover safety, a 3 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?

The description is concise, two sentences, and front-loaded with the purpose. It wastes no words, but could be slightly more structured by explicitly listing parameters. Still, it is efficient and clear.

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 3 parameters, no output schema, and no schema descriptions, the description is somewhat incomplete. It explains the 'conversation' parameter's purpose but not 'context' or the exact format of 'conversation' (string vs array). The tool is simple, but the description could be more complete for an agent to use it 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 description coverage is 0%, so the description must compensate. The description mentions 'conversation array' but the schema has a 'conversation' parameter of type string with default '[]', which is not clearly explained. The 'context' parameter is not mentioned at all. The description adds minimal meaning beyond the schema, leaving the agent uncertain about how to fill 'context' and 'conversation'.

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: 'Report a bug, missing feature, or send feedback.' It uses a specific verb ('report') and resource ('bug'), and distinguishes from siblings by covering feedback and missing features, which are not implied by sibling names like 'agger_list_accounts' or 'authenticate'.

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 the tool (when reporting bugs, missing features, or feedback) but does not explicitly state when not to use it or mention alternatives. It provides a hint about including the conversation array for reproduction, which is useful but not a full usage guideline.

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, idempotentHint=true, and destructiveHint=false, which cover the safety profile. The description adds no extra context beyond confirming it shows information, but it does not contradict annotations, so a baseline score of 3 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?

The description is a single, succinct sentence that front-loads the verb and resource with zero wasted words. It is perfectly concise for the tool's trivial 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?

For a simple version query with no parameters, no output schema, and thorough annotations, the description fully satisfies the need. It clearly states what the tool does without requiring additional behavioral details.

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 the schema reflects that with an empty properties object. Per rubric, 0 parameters earns a baseline score of 4. The description adds no parameter info because none exist, which is sufficient.

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 'Show' and the resource 'current MCP platform and adapter versions', making the tool's purpose unambiguous. It is distinct from sibling tools which involve listing accounts, authentication, connecting, marketplace, reporting bugs, or getting toolkit info.

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 (to view version info) and there are no alternative tools for this specific purpose, so no explicit when-not guidance is needed. The simplicity of the tool makes the intended context obvious.

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, idempotentHint=true, and destructiveHint=false, which fully covers the safe, read-only nature. The description adds specific behavioral details about what is returned (the exact state elements), which is valuable beyond the annotations. No contradictions found.

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, focused sentence that lists all key information without redundancy. It is front-loaded with the purpose and immediately provides the return contents. Every word earns its place, and it is highly readable.

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 simplicity (zero parameters, no output schema), the description is fully complete. It tells the agent exactly what information to expect, which is sufficient for selection and invocation. There is nothing missing for this level of 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 has no parameters, so the description carries no parameter burden. The baseline of 4 applies for a zero-parameter tool; the description does not need to add anything. It does not provide any misleading parameter information.

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 specifies the tool's purpose with a clear verb ('Returns') and resource ('current toolkit state'), and enumerates the exact contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from siblings like show_version (version info) and agger_list_accounts (account-specific listing).

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 implicitly communicates that this is for retrieving a high-level overview of the toolkit, useful when the agent needs a snapshot of MCPs and accounts. It does not explicitly state when not to use it (e.g., for specific account details), but the context from sibling names (agger_list_accounts) provides a clear alternative. Minor gap: no explicit 'use this instead of X' guidance.

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