Opus Growth, Ad Platforms MCP Connector

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

Beyond the annotations (readOnlyHint, openWorldHint, destructiveHint), the description explains concrete behaviors: the gateway NEVER writes, write attempts are refused with a directive to use call_write_tool, arguments are validated server-side and produce precise errors, and credits/access rules match direct invocation. This meaningfully extends the annotation-only profile without 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?

The description is dense but purposeful, front-loading the core purpose and read-only guarantee before the usage workflow. Every sentence contributes useful information, such as the discovery prerequisite, validation behavior, and write-refusal routing. No filler or redundancy.

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 gateway tool with dynamic targets, the description is complete: it explains how to discover target tools, what data domains are reachable, how writes are blocked, how errors are surfaced, and how credits behave. The presence of an output schema means return-value details are not required here.

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%, so the description carries the full burden for parameter meaning. It explicitly defines both parameters: 'name = exact tool name' and 'arguments = that tool's parameters as an object.' It also explains that arguments are validated against the target tool's schema, compensating well for the absence of 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 the tool's purpose: 'Run a READ-ONLY Opus tool by name — the gateway to every reporting/listing capability that is not in your visible core set.' It specifies a verb, a resource, and a scope, and distinguishes itself from the sibling call_write_tool by emphasizing read-only behavior.

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 gives explicit guidance: use search_tools(query) FIRST to discover the exact tool name and schema, then call this gateway. It also states when not to use it — if the named tool modifies data, it is refused and call_write_tool should be used instead. This clearly routes the agent between alternatives.

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?

The description goes beyond the annotations by disclosing the destinations (advertising platform APIs and Opus Growth's hosting/WordPress), the preview-and-confirm gate, and the credit/access behavior. It confirms the destructiveHint by framing this as the write gateway, and clearly states read-only calls are rejected.

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 longer than average but every sentence carries essential routing or behavior information, and it is front-loaded with the purpose and core workflow. There is no filler or repeated schema 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 generic write dispatcher with a low-coverage schema, the description covers the prerequisite lookup, parameter meaning, target systems, read-only exclusion, confirmation gate, and access rules. Nothing needed for correct invocation is missing, and the presence of an output schema means return details do not need to be re-explained.

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 alone only shows generic `name` and `arguments` fields with no descriptions; the description compensates by defining `name` as the exact tool name from search_tools and `arguments` as that tool's parameter object. It also tells the agent where to discover the parameter schema, which is the only viable guidance for a dynamic dispatcher.

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 operation ('Run a WRITING Opus tool by name') and enumerates the write categories it covers, so an agent immediately knows this is the generic write dispatcher. It also separates itself from siblings by stating that read-only tools are refused and belong on call_tool, and that search_tools should provide the exact name.

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 gives an explicit before-use workflow: call search_tools(query) first to get the exact name and argument schema, then invoke this tool. It also states the exclusion condition ('Read-only tools are refused here') and names call_tool as the alternative.

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 and destructiveHint, and the description adds 'Read-only, costs nothing' plus a detailed account of the two behaviors (no argument vs. platform). It does not contradict annotations and provides useful operational context beyond the structured 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?

Three dense sentences, front-loaded with purpose, then behavior, then when-to-use. Every clause adds value; no filler or redundant restating of the 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?

For a one-optional-parameter introspection tool with an output schema, the description fully covers what happens with and without the parameter, what the return contains, and when to call it. Nothing essential 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 has one optional 'platform' with no description (0% coverage), so the description carries the burden. It clearly explains that omitting platform lists every supported platform, while passing platform returns platform-specific fields like account-id, row levels, breakdown dimensions, and entity types.

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?

Description uses a specific verb ('Explains') and names the exact resource: the unified read tools' capabilities. It distinguishes two modes (no argument vs. platform) and mentions the specific functions it introspects (get_report / list_entities), making it clearly different from sibling tools like get_report or list_entities.

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?

Gives an explicit call condition: 'Call this whenever you are unsure which level/breakdown/entity name to pass.' This directly tells an agent when to invoke describe instead of guessing parameters or trying 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?

Annotations already declare readOnlyHint and destructiveHint, and the description adds value by explaining the tool expands a search result, the expected id format, and the return shape. This goes beyond the annotations, clarifying behavior without contradicting them.

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, information-dense sentence that front-loads the purpose and includes the output shape. It is concise and well-structured, though splitting into separate sentences for input and output might improve readability slightly.

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 an output schema exists (as indicated by context signals), the description does not need to detail return values, but it does provide a preview. It covers the input format, purpose, and read-only nature. It does not discuss error cases or prerequisites, but these are not critical for a simple fetch operation.

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%, but the description compensates by explaining the `id` parameter must be a 'platform:account_id' from a search result. This provides essential semantic meaning that the schema lacks.

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 ('Expands'), a clear resource (a search result id into account details), and lists the fields returned (account name, id, currency/status). It also specifies the exact input format ('platform:account_id') and output structure, making the tool's purpose unmistakable.

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 the tool is used after a `search` call, but it does not explicitly mention when NOT to use it or compare with sibling tools like list_accounts or get_report. It gives context (read-only, expands search result) but lacks explicit 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral detail beyond annotations: the unified multi-platform scope, default account behavior when left empty, and the subtle Search Console behavior that rows are only ever returned by clicks unless a sort is specified. This meaningfully exceeds what annotations alone provide.

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 flame every sentence adds parametrical or behavioral value, and the primary purpose is front-loaded in the first sentence. The run-on semicolon style makes it slightly harder to parse, but the content is appropriately sized for an 8-parameter unified tool with cross-platform nuances.

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 tool with 8 parameters and an output schema, the description is complete enough: every operationally important parameter is explained, platform-specific nuances are disclosed, and the output is summarized as the platform's metric rows. The presence of an output schema means return-value details need not be spelled out, so no critical context 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 description coverage is 0%, so the description must carry the full parameter burden, and it does. It explains platform values, account ID semantics across platforms, days versus start_date/end_date, level values, breakdown dimensions, and the special Search Console combination/sort syntax. Only 'limit' is left to inference, which is reasonable since it is self-explanatory from 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 uses a specific verb+resource ('report tool for EVERY connected platform') and explicitly scopes it to 'how did X perform' questions slash 'Returns the platform's metric rows.' It clearly differentiates from the sibling search/list tools by positioning itself as the unified reporting entry point rather than a platform-specific or metadata 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 gives explicit usage guidance: use for any performance question, pass platform/account/days/level/breakdown, and call describe(platform) to see supported options. It provides clear context and points to an alternative (describe) for discovering platform specifics, though it does not list explicit when-not-to-use cases or name a concrete sibling tool as the alternative.

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 mark the tool readOnly and non-destructive; the description adds the key behavioral facts beyond that: the response carries default_account_id, all_accessible expands under MCC, and platform has a default-and-redirect behavior. No contradiction 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?

Every clause earns its place: core purpose, default scope, the all_accessible toggle, and platform routing are each specified once with no filler. Information is front-loaded, with the most essential behavior first.

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?

The definition fully equips an agent to call the tool correctly: both parameters are semantically covered, output schema supplies return shape, and annotations supply safety/open-world context. Nothing needed for invocation is missing, and the cross-platform routing prevents misuse.

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 carries the full burden for both parameters. It explains platform's optional/default nature, enumerates accepted platform values, and clarifies all_accessible=false/true semantics, including MCC client expansion.

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: 'Lists the user's connected Google Ads account(s).' It immediately distinguishes scoped behavior (connected/selected accounts) from all_accessible behavior, and clarifies that naming a different platform redirects to that platform's own tool, so an agent can tell it apart from list_entities and platform-specific 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?

It gives clear usage context: default returns only accounts selected at connect time, while all_accessible=true expands to all reachable accounts, including MCC clients. It also explains how to delegate to another platform's account-listing tool, though it does not name sibling tools explicitly or include when-not-to-use exclusions.

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 and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond that: paging semantics (rows is one page, total_rows is real count, truncated=true means merge), flat-row return format for keywords/ads, bid-related caveats (max_cpc, bid_source override), and the critical distinction between is_serving and status=ENABLED. This is rich, non-obvious behavior that an agent must know to use the tool correctly.

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 every section earns its place: the opening paragraph defines scope and parameters, and the Google Ads specifics section covers paging, bids, and status semantics that are essential for correct use. It is front-loaded with the core purpose and parameter overview before diving into platform-specific details. It could be slightly tighter, but the density of critical operational information justifies the length.

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 (7 parameters, 5 platforms, multiple entity types, paging, bid semantics, status semantics) and the presence of an output schema, the description is remarkably complete. It covers parameter meaning, platform differences, paging behavior, return-format caveats, and the active-vs-enabled trap. The only minor gap is that it doesn't describe the output schema structure in prose, but the output schema exists and the description explicitly mentions key fields (total_rows, serving_count, serving_summary, is_serving, status_reasons, etc.).

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 carries the full burden of explaining parameters. It explains platform, entity, account, parent_id, and the Google Ads customer_id alias, plus limit/offset paging semantics. It does not explicitly describe the 'limit' and 'offset' defaults in prose, but the schema provides defaults and the paging section covers their meaning. This is strong compensation for the 0% schema 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 opens with a specific verb and resource ('Lists the entities ... of ANY connected ad platform with their IDs') and explicitly distinguishes itself from platform-specific list tools, telling the agent to use this instead. It enumerates the entity types per platform, so an agent can immediately tell what this tool covers and that it is the generic cross-platform list tool among the 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?

The description gives explicit when-to-use guidance ('use this instead of looking for a platform-specific list tool'), explains how to disambiguate entity names per platform, and provides platform-specific operational guidance (e.g., Google Ads paging, active vs. enabled status). It also tells the agent to call describe(platform) to see accepted entity names, which is a clear alternative/fallback path.

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 indicate a read-only, non-destructive, open-world operation. The description adds meaningful behavioral context beyond annotations: the result set mixes managed hosting servers with user-owned WordPress sites, and both are editable through different tool families. No contradictions with annotations are present.

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 main purpose is front-loaded in the first sentence, and the second paragraph earns its place by explaining the important distinction between the two result types and the relevant edit tool families. There is no filler or redundant restatement.

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 empty schema, the read-only annotations, and the output schema, the description fully covers what an agent needs: what is listed, the two categories of resources, and how to act on each afterward. Nothing essential 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 has zero parameters, so there is nothing for the description to clarify. The baseline of 4 applies because no parameter documentation burden exists.

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: it lists the websites the user can edit. It clearly distinguishes between Opus Growth hosting servers and connected WordPress sites, and even names the tool families used to edit each. This allows an agent to differentiate it from sibling tools like list_accounts without opening schemas.

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 the two kinds of results and which edit tool families apply to each, giving clear context for when this tool is relevant. It does not explicitly name alternatives or say 'use this instead of list_accounts', but the context is strong enough for an agent to infer when to call it.

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 readOnlyHint=false and destructiveHint=false; the description adds that it saves data, that it's a prerequisite for change operations, and provides phone format (E.164) and country_code meaning. It doesn't detail repeated-call behavior, but the annotations already cover the safety profile, and the description adds useful context.

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 moderately long but every sentence adds value: purpose, alternative, format, and idempotency. It is front-loaded with the main action and ends with practical details. No unnecessary fluff.

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 save operation, it covers purpose, prerequisites, and parameter formats. It doesn't describe the return value, but an output schema exists, so that is not a gap. It could explicitly state that phone is optional if not provided, but the schema already shows defaults. Overall, it is adequately 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 schema has 0% description coverage, so the description must explain parameters. It does explain phone format (E.164) and country_code (dialing code), and implies first_name/last_name via 'full name'. However, it doesn't clarify that only first_name is required while phone and others are optional, which could cause confusion since it says 'saves ... phone number'. It still adds format details 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 the action (saves the account owner's full name and phone number) and its purpose (unlocking operations that change an ad account). It also distinguishes itself from read-only tools by explicitly stating it is not required for view/list/report tools, helping an agent pick the right 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?

It gives explicit when-to-use guidance: it is needed to enable operations that modify an ad account (creating/updating/pausing campaigns, budgets, statuses), and it is not needed for read-only tools. It also mentions an alternative (panel) and states that calling once is enough, which is clear direction.

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 mark this as non-read-only and non-destructive, and the description adds useful behavioral context: the user receives an email on resolution, and synonyms are accepted to prevent lost reports. This goes beyond the annotation fields without contradicting them.

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 compact sentences lead with the purpose, then cover required parameters and edge-case aliases. There is no fluff; the extra explanation about synonyms 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 reporting tool, the description covers purpose, parameters, aliases, and side effects. It doesn't explain whether at least one of summary/details is expected, but the output schema and annotations cover the remaining context, so this is a minor gap.

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 description coverage, the description carries the full burden and does compensate: it explains summary, tool_name, details, and all three synonyms. It is slightly vague about which synonyms map to which field, but it still meaningfully documents every 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 uses a specific verb ('Reports') and names the exact resource ('a bug or unexpected failure to Opus Growth support'), which makes the tool's job unmistakable. The content is clearly distinct from sibling tools like get_report or call_tool even without naming 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 description clearly states the intended trigger (bug or unexpected failure) and how to structure the report (summary, tool_name, details). It does not explicitly contrast with alternatives or give negative guidance, but the use case is clear enough.

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 cover read-only and non-destructive behavior, so the bar is lower. The description adds valuable non-obvious context: it does not consume billing, empty queries list all accounts, and results are limited to a specific shape. This goes beyond what the annotations alone provide.

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 compact, front-loads the core purpose, and every sentence adds useful information: scope, empty-query behavior, safety/billing, return format, and the next step. No filler or redundancy is present.

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 single optional parameter, annotations, and the included output format, the description is fully adequate for an agent to select and invoke the tool correctly. It even provides cross-tool guidance to `fetch`, making the workflow 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?

Schema description coverage is 0%, so the description must carry parameter meaning. It effectively explains the sole `query` parameter by stating that matching accounts are returned and that an empty query lists all connected accounts. This is sufficient for the single optional 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 clearly states a specific verb ('Searches') and resource ('connected ad accounts' from Google, Meta, LinkedIn) and defines the return as matching accounts. It is unambiguous about what the tool does, though it does not explicitly distinguish itself from sibling tools like list_accounts or search_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?

The description provides clear context for when to use the tool: search or list connected ad accounts, including the empty-query behavior. It also routes the agent to `fetch` for details, but it does not explicitly state when not to use this tool or name alternatives such as list_accounts.

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 and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context: it returns matching tool names, descriptions, and full JSON argument schemas, and it positions the tool as a non-executing catalog lookup. No contradiction 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 dense but every sentence earns its place: purpose, when-to-use, return value, and parameter semantics. It is front-loaded with the key purpose and avoids filler 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?

The tool is simple and has an output schema, so return-value details are not required. The description covers purpose, usage workflow, examples, and query semantics. The only minor gap is that the limit parameter is never mentioned, but the tool remains callable correctly with the information provided.

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 schema description coverage at 0%, the description must carry the burden. It explains the query parameter well ('plain language' plus three concrete examples), but it does not explain the limit parameter at all, leaving the agent to infer its meaning from the default value of 8.

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: 'Find the right Opus tool from the FULL catalog.' It clearly differentiates itself from the chat's core tool set and from call_tool by framing itself as a discovery step that returns tool metadata rather than executing an action.

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 when to use the tool: 'for ANYTHING else... search here FIRST.' It also gives a concrete workflow ('then run the tool with call_tool') and provides example queries. This is direct, actionable usage guidance that leaves little to inference.

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