Server Quality Checklist

Tool Scores

• sync_loadA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses the source (remote git), the target (.context/ files), and the output (return contents), but it does not clarify whether local files are overwritten, whether authentication or network access is required, or what happens if no remote context exists. More side-effect disclosure would strengthen this.

  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 compact and front-loaded: first sentence states purpose, second gives usage context, third provides an exclusion. Every sentence contributes without 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?

  For a tool with only two optional parameters and no output schema, the description covers purpose, invocation triggers, and result type. It could be more complete by noting side effects on local files, but the essentials for selecting and invoking the tool are present.

  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 coverage is 100%, and both parameters have meaningful descriptions in the schema. The description itself adds no additional parameter detail, so 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 states a clear action ('Pull latest .context/ files from remote git') and an explicit result ('return their contents'). It also names concrete request aliases, making the tool's purpose immediately recognizable and distinguishable from its siblings.

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

  Usage Guidelines5/5

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

  The description explicitly enumerates when to use the tool ('load/pull/restore/recover requests') with concrete examples, and explicitly warns against using sync_push for these requests. This gives an agent unambiguous selection guidance.

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

• write_contextA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full disclosure burden. It clearly states the mutation ('write ... to .context/ files') and distinguishes additive append from replacing overwrite, which is meaningful behavioral context. However, it does not warn that overwrite discards existing content or describe what happens on repeated writes, so the destructive edge of the tool is only implied, not disclosed.

  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?

  Three sentences, roughly 40 words, with the core action front-loaded and every sentence earning its place: what it does, mode-to-file mapping, and usage intent. It repeats nothing from the schema and contains no filler.

  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 two-parameter tool with no output schema and no annotations, the description covers the operation, both modes, and the intended use case, while the 100%-covered schema handles parameter details including project_path resolution. The only notable gap is the unstated destructive consequence of overwrite, which is already accounted for under behavioral transparency.

  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?

  Schema description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by pairing action enum values with specific file enum values — guidance the schema does not provide — so agents know e.g. to append gotchas and overwrite progress. This mapping meaningfully reduces ambiguity in constructing entries.

  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 opens with a specific verb and resource — 'Batch write memory entries to .context/ files' — and immediately differentiates the two write modes. It clearly distinguishes from the sync_* siblings (sync_init, sync_push, sync_load), which handle context synchronization rather than writing memory entries, so an agent can select this tool without opening the schema.

  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?

  'Use this to record discoveries, decisions, and progress during development' is an explicit when-to-use signal, and the append/overwrite mapping ('append for gotchas, architecture, api_notes; overwrite for progress, summary') routes the agent to the correct mode per file type. It does not name alternatives or state when not to use it, but the context is clear enough that exclusions are not critical.

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

• sync_initA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full disclosure burden. It discloses the critical safety behavior — it will not overwrite existing context — plus the redirect behavior to sync_load. It does not detail what files are created or what the tool returns, but the most decision-relevant behavioral trait is clearly stated.

  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?

  Three sentences with zero filler: purpose first, trigger conditions second, exclusion and alternative third. Every sentence earns its place, and the most decision-relevant information — when not to use the tool — is unambiguously stated.

  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 tool with four optional, fully schema-documented parameters and no output schema, the description covers the essential decision factors: purpose, trigger phrases, exclusion criteria, and the no-overwrite safeguard. The only minor omission is expected return/output behavior, a small gap given the tool's low complexity.

  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 all four optional parameters (summary, progress, auto_push, project_path) fully documented in the input schema, so the baseline of 3 applies. The description adds no parameter-level detail, but none is needed given the schema's completeness.

  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 opens with a specific verb and resource — 'Bootstrap Context Sync' — and scopes it to 'a project that has not been initialized yet.' It explicitly names the sibling sync_load as the destination for existing contexts, so an agent can distinguish the tools without inspecting their schemas.

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

  Usage Guidelines5/5

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

  Provides explicit when-to-use guidance with concrete trigger phrases ('/sync-init', 'init context', 'initialize sync', 'set up context sync for this repo') and an explicit exclusion: 'If context already exists, do not overwrite it; guide the user to /sync-load instead.' This names the alternative and the condition that selects it, leaving nothing to inference.

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

• sync_pushA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses the core behavior (pushing local .context/ files to remote git) and an important side effect (auto-generating SUMMARY.md). It could add more detail about destructive effects, commit behavior, or git prerequisites, but the described behavior is specific and not misleading.

  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?

  Three sentences, front-loaded with the core action, followed by explicit usage triggers and exclusions. No filler or redundant restatement of the parameter schema.

  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 mutation tool with no annotations and no output schema, the description covers the core action, the generated artifact, and when to use it. Minor gaps remain, such as git prerequisites, branch behavior, or failure semantics, but the essential information for correct invocation is present.

  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 covers both parameters fully (100%), so the description does not need to repeat them. The description adds the context that SUMMARY.md is auto-generated, which aligns with the summary parameter, but it does not add meaning beyond what the schema already provides. Baseline 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 states a specific verb ('Push'), a concrete resource ('local .context/ files'), and a target ('remote git'), and adds that SUMMARY.md is auto-generated. It clearly differentiates itself from sibling tools by framing itself as the save/upload/push operation and explicitly excluding pull/load/restore scenarios.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use triggers such as '/sync-save', 'sync push', 'save context', and 'upload context', and explicitly says not to use it for pull/load/restore/new-device recovery. This is strong routing guidance that prevents misuse.

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