Server Quality Checklist

Tool Scores

• docs_createC
  2.7/5.0
  Behavior2/5

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

  The description adds the useful detail that the tool verifies initial content, and annotations already indicate this is a mutating, non-idempotent call. However, it never explains the destructiveHint=true annotation, which is significant and potentially surprising for a create operation; an agent is left uncertain about what side effects beyond creation might occur.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single front-loaded sentence with no filler. It states the core action first and packs the important 'private native' and 'verify initial content' details efficiently.

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

  Completeness2/5

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

  Given that this is a 3-parameter tool with 0% schema coverage and no usage guidance, the description leaves too much unresolved for an agent to invoke it correctly. The output schema may cover return values, but parameter semantics, routing guidance, and side-effect transparency are still missing.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  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, but it does not mention the title, markdown, or format_profile parameters. The phrase 'initial content' hints at markdown but leaves all parameter semantics, defaults, and the format_profile enum unexplained.

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

  Purpose4/5

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

  The description clearly identifies the action ('Create') and the resource ('private native Google document'), and it adds a post-condition ('verify its initial content'). The verb alone distinguishes it from the sibling tools docs_read, docs_replace_markdown, and docs_edit_text, though it doesn't explicitly name those alternatives.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides no guidance on when to use this tool versus the alternatives, no prerequisites, and no exclusions. The only implicit signal is the verb 'create,' which is not enough for an agent to make a confident routing decision.

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

• docs_replace_markdownB
  3.1/5.0
  Behavior3/5

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

  Annotations already indicate this is destructive and non-idempotent, so the description does not need to restate mutation. It adds useful context about the revision guard and scoping to a single tab, but it does not disclose behavior on a stale revision mismatch or the full extent of what is overwritten.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single compact sentence with no filler, front-loading the verb and object. It loses a point for the slightly awkward 'from Markdown' phrasing and for omitting a bit of useful structural guidance, but it is otherwise efficiently written.

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

  Completeness2/5

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

  For a destructive write operation with five parameters, zero schema description coverage, and an exact-revision guard, one sentence is not enough. Missing context includes format_profile semantics, tab selection when tab_id is null, revision-mismatch behavior, and how this differs from docs_edit_text.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  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 for the five parameters, and it only loosely clarifies the roles of markdown and expected_revision_id. It does not explain tab_id null behavior, format_profile choices, or how the replacement target is selected when tab_id is absent.

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

  Purpose4/5

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

  The description states a specific action ('Replace'), a clear object ('one document tab'), and the input format ('from Markdown'), which makes the core operation understandable. It is reasonably distinct from siblings like docs_read and docs_create, though it does not explicitly differentiate from docs_edit_text.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Usage context is only implied by the phrase 'under an exact revision guard,' suggesting a controlled overwrite. There is no explicit statement about when to prefer this over docs_edit_text or what conditions disqualify its use, so guidance remains implicit rather than direct.

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

• docs_edit_textA
  3.8/5.0
  Behavior4/5

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

  Annotations already provide destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds meaningful behavior beyond those flags: the operation can be previewed or applied, matching is exact, and it is revision-guarded. It does not disclose partial-application or expected_count mismatch behavior, which prevents a 5.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single front-loaded sentence with no filler; every phrase adds information about behavior, exactness, or scope. 'In one tab' is slightly terse, but the overall structure is appropriately compact.

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

  Completeness3/5

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

  For a destructive mutation tool with an output schema and annotations, the main action is named and the revision-guard concept is present. However, the description does not clarify how expected_count is used, what 'one tab' means in relation to tab_id, or the exact contract of expected_revision_id, so it is adequate but not complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the prose must carry parameter semantics, but it only gestures at apply ('preview or apply') and expected_revision_id ('revision-guarded'). It leaves expected_count, tab_id, document, and the replacement structure to inference, which is not enough compensation for an undocumented schema.

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

  Purpose5/5

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

  The description states a specific operation ('preview or apply exact, revision-guarded replacements') on a clearly identified resource (text in a document/tab). The qualifier 'exact, revision-guarded' distinguishes it from the markdown-style sibling without being a tautology.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The wording implies this is for exact, revision-checked text replacements and supports a preview-before-apply workflow, but it does not explicitly say when to choose this over docs_replace_markdown or docs_create. Exclusion conditions and alternative tools are not named in the description, so usage guidance is only implicit.

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

• docs_readA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior. The description adds useful context that reads are bounded and include tab metadata and revision info, going beyond the safety profile without contradicting it.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single, tight sentence that front-loads the action and resource. There is no filler, and every phrase adds meaning.

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

  Completeness3/5

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

  The presence of an output schema and safety annotations covers return values and side effects, but the description leaves the semantics of start and tab selection underspecified. An agent can call the tool but may not know how to control the read window or target a specific tab without additional inference.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  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 explanatory burden. It only hints at 'bounded content' (max_chars) and 'tab metadata' (tab_id), leaving start, document, and default behavior unexplained. This is insufficient for a 4-parameter tool.

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

  Purpose5/5

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

  The description states a specific verb (Read) and concrete resources (bounded content, tab metadata, current Docs revision), which clearly distinguishes it from the write-oriented siblings docs_create, docs_replace_markdown, and docs_edit_text.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The use case is implied by the verb 'Read' and the contrast with sibling write tools, but the description does not explicitly state when to prefer this tool or when not to use alternatives. There are no exclusions or named alternatives.

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