Server Quality Checklist

Tool Scores

• weekly_summaryA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It adds useful behavioral context: 'Only reports observed work' and 'real activity' imply a read-only, evidence-based aggregation. However, it does not explicitly state side-effect-freedom, output format details, or clarify what 'reviews' means, leaving some ambiguity.

  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 three short sentences, each earning its place: the first defines the output and grouping, the second lists use cases, and the third adds a key constraint. It is front-loaded with the primary verb and resource.

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

  Completeness4/5

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

  For a simple tool with one optional parameter and no output schema, the description provides a solid sense of the output structure (accomplishments grouped by status, with reviews and totals) and the data source constraint. It does not explain what 'reviews' entails, but overall it is sufficiently complete for an agent to select and invoke the tool.

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

  Parameters3/5

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

  The schema description covers 100% of the one parameter (days) with min/max and default, so the description adds limited extra value. Mentioning 'any N days' aligns with the parameter but does not introduce new syntax or constraints beyond the 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 clearly states the tool rolls up activity into accomplishments, grouped by work item as Shipped vs In progress, with reviews and totals. This specific verb+resource structure distinguishes it from siblings like activity_digest or standup_draft, which focus on raw activity or daily updates.

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

  Usage Guidelines4/5

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

  It explicitly names intended use cases: 'For 1:1s, weekly status, and self-reviews.' It also implies when not to use it via 'Only reports observed work,' indicating it is not for planned or speculative activity. However, it does not explicitly name alternatives or exclusion criteria beyond that.

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

• activity_digestA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral transparency burden. It discloses output ordering (newest first), grouping (by day), and cross-tool scope (across the configured tools), which goes beyond the schema. While it doesn't explicitly state 'read-only', the digest nature strongly implies a non-mutating query.

  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?

  Two sentences, front-loaded with the core purpose and directly followed by a usage directive. No redundant or filler wording; each clause contributes meaningful information about the tool's behavior.

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

  Completeness4/5

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

  The tool is simple (2 optional params, no output schema) and the description explains the return structure and scope adequately. It mentions default window indirectly via schema, and sibling tools like standup_draft and weekly_summary provide additional context for when this digest is the right choice.

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

  Parameters3/5

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

  Schema descriptions cover 100% of parameters, explaining 'days' as look-back and 'since' as an ISO start override with default behavior. The description itself doesn't mention parameters, but with full schema coverage, the baseline score of 3 is appropriate.

  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 clearly identifies the tool as 'a chronological digest of everything you did' with explicit format details (newest first, grouped by day) and scope (across configured tools). It also distinguishes itself from the 'opinionated standup framing', which differentiates it from sibling tool standup_draft.

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

  Usage Guidelines4/5

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

  The description explicitly says 'Use it to reconstruct what actually happened' and contrasts it with standup framing, giving a clear use case. It doesn't name alternatives directly, but the context and sibling tool names make the appropriate choice apparent.

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

• blocker_scanA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It goes beyond a simple action by explaining the detection mechanism: 'Detects blockers from signals, not self-report' and lists specific signal types (explicit language, PRs awaiting review, unmoved tickets, help requests). It also mentions 'ranked by severity,' indicating output ordering. While it does not explicitly state side effects, the nature of a scan tool implies read-only behavior, and the description provides meaningful insight into how the tool operates.

  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 two sentences: the first delivers the primary purpose and scope, the second explains the detection methodology. It is concise, front-loaded, and every phrase adds value. No unnecessary filler or redundancy.

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

  Completeness4/5

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

  Given the tool's complexity—scanning four platforms with multiple signal types and no output schema—the description provides a clear overview of what it does and how it detects blockers. It states the result is ranked by severity, which gives an expectation of the output structure. However, it does not detail the exact format of the returned blockers (e.g., grouping by source, severity levels, or links), so a bit more information would enhance completeness.

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

  Parameters3/5

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

  Schema description coverage is 100%, with both 'days' and 'since' well-documented in the input schema. The description does not add additional parameter-level meaning beyond the schema; it merely references the default window in a way that mirrors the schema. Since the schema carries the full burden, a baseline score of 3 is appropriate.

  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 clearly states the tool's function: 'Surface what is blocking you across GitHub, Jira, Linear, and Slack, ranked by severity.' This is a specific verb+resource+scope that distinguishes it from sibling tools like weekly_summary or activity_digest, which likely provide general summaries rather than blocker-specific information. The signal-based detection further clarifies its unique positioning.

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

  Usage Guidelines4/5

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

  The description implies when to use this tool: when you need to identify blockers across multiple platforms, especially via signals rather than self-report. It does not explicitly name alternatives or state when not to use it, but the focused purpose ('what is blocking you') provides clear context. The inclusion of detection signals gives additional guidance on the tool's suitability for a given situation.

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

• standup_draftA
  4.4/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden of disclosing behavioral traits. It explicitly states 'Only reports observed activity; never invents work,' which is a strong transparency guarantee against hallucinated content. It also discloses the default window behavior (Monday reaches back across the weekend) and the output structure (Yesterday/Today/Blockers grouped by work item). These are valuable beyond what the schema provides.

  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 three well-structured sentences with no redundancy. It front-loads the core purpose, then details output format and behavioral constraints. Every sentence earns its place.

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

  Completeness4/5

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

  The description covers the essential context: what the tool does, what it returns, and default behavior. Since there is no output schema, the description appropriately summarizes the return format. It omits potential edge cases (e.g., no activity found, missing integrations), but for a straightforward standup generator, it is sufficiently complete for an agent to select and invoke it correctly.

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

  Parameters3/5

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

  The schema already provides complete descriptions for both parameters ('days' and 'since'), including default behavior. The description adds minimal extra meaning about the parameters themselves; the comment about the default window is corroborated by the schema, not supplementary. With 100% schema coverage, a baseline of 3 is appropriate.

  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 clearly states the tool's purpose with a specific verb and resource: 'Generate your daily standup' from real activity. It also distinguishes itself from siblings by emphasizing daily frequency, grouping by work item not tool, and returning concrete deltas. This makes 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.

  Usage Guidelines4/5

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

  The description provides clear context on when to use the tool: to generate a daily standup from observed activity. It implies the temporal scope ('Defaults to the last working day') and differentiates from weekly or broader summaries, but it doesn't explicitly name alternatives or state when not to use this tool. This is clear but lacks explicit exclusions.

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

• list_sourcesA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It explicitly states that the tool does not hit the network and may show demo data, which is important behavioral context. It doesn't detail the output format, but for a simple list tool this is adequate.

  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?

  Two sentences, no fluff. The main action is first, followed by a clarifying caveat about network behavior and an alternative command.

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

  Completeness5/5

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

  For a tool with no parameters and no output schema, this description is complete: it covers purpose, scope, and key behavioral limitation (no network), which is all the context needed to select and invoke correctly.

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

  Parameters4/5

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

  There are zero parameters, so the baseline is 4. The description adds meaning by explaining what 'sources' refers to (GitHub, Jira, Linear, Slack) and the demo data condition, which effectively serves as the parameter-free documentation.

  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 uses a specific verb ('Show') and identifies the resource (activity sources), listing example sources and the demo data state. This clearly distinguishes it from sibling tools like standup_draft or blocker_scan.

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

  Usage Guidelines4/5

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

  It explains that this tool does not hit the network and suggests running the server with --check for live connection verification, which gives clear context on when to use this static listing versus a live check. However, it does not explicitly name sibling tools or say 'use this when...'.

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