Server Quality Checklist

Tool Scores

• pond_get_messageA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare the tool read-only and idempotent. The description adds meaningful behavioral context by explaining the output includes full part bodies and that context_before/context_after control neighbor inclusion (default 3, like grep -B/-A). No contradiction is present.

  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 sentences, front-loaded with the primary action, and every sentence earns its place. It packs core semantics, usage guidance, and a sibling pointer without waste.

  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 only 3 parameters, no output schema, and strong annotations, the description covers what the tool does, how to identify the target message, the behavior of optional parameters, and a pointer to the alternative for broader context. It also points to a resource schema for response format details, making it complete.

  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 coverage is 100%, but the description enriches parameter meaning by explaining id can come from pond_search or transcript, and by giving the grep analogy for context_before/context_after defaults. This adds value beyond the bare schema descriptions.

  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 ('Expand') with a clear resource ('one message') and details what expansion includes (full part bodies: tool_call/tool_result/reasoning/file) plus conversational neighbors. It also distinguishes from sibling tools by explicitly pointing to pond_get_session for whole-session retrieval.

  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 clearly instructs how to obtain the message_id (from pond_search or a transcript line) and names an alternative tool for whole-session needs ('For the whole session use pond_get_session'). It doesn't explicitly state when not to use it, but the context is unambiguous enough.

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

• pond_searchA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare read-only and idempotent, and the description adds substantial behavioral detail: vector mode fallback to fts, scored hits grouped by session with best-first ordering, conversational-text-only scope, subagent exclusion with deliberate opt-in via source_agent subpath, and no pagination (limit as knob). 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.

  Conciseness5/5

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

  Four dense sentences, each earning its place: purpose/examples, modes, scoping/filters, output/navigation, exclusions. Well front-loaded and free of fluff.

  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?

  Despite lacking an output schema, the description explains return structure (scored hits grouped by session), how to access full messages, and the expected gap for excluded content. It also points to a resource schema for further response details. Given the tool's complexity, this is complete.

  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% with rich per-parameter descriptions. The main description reinforces a few concepts (semantic query, mode meaning, scoping filters) but adds limited new parameter-level detail beyond the schema. Baseline 3 is appropriate since the schema carries the heavy lifting.

  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?

  Description opens with a specific verb+resource: 'Find relevant messages in past sessions' and positions it as 'the entry point for recall' with example queries. It further distinguishes from siblings by directing users to pond_get_session/pond_get_message for reading hits and to pond_sql for excluded content.

  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?

  Explicitly defines when to use: entry point for recall queries. Clearly states what is excluded (tool calls/results, reasoning, subagent sessions) and points to pond_sql for those cases, giving concrete when-not-to-use guidance. Also explains mode choices (vector vs fts) and scoping filters.

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

• pond_get_sessionA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint and idempotentHint, but the description adds substantial behavioral context: chronological ordering, paging semantics, from="end" reading final state, subagent footer listing, and that message_id resolves to parent session. It also warns about late conclusions superseding early ones.

  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 dense but every sentence serves a purpose: purpose, id resolution, paging, subagent navigation, and bulk-export exclusion. It is front-loaded with the core purpose and avoids 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 tool with no output schema and nontrivial paging, the description covers the key aspects: content of the transcript, paging methods, id sources, and subagent handling. It points to resource schema://pond for return format, but does not detail response fields. Slight gap, but still robust enough for an agent to select and invoke correctly.

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

  Parameters5/5

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

  Though schema coverage is 100%, the description significantly enriches parameter meaning: it explains that message_id resolves to parent session, from="end" reads most recent turns first, and describes how after_message_id/before_message_id act as page markers. This goes far beyond the schema's basic field definitions.

  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: "Read a whole past session as a chronological transcript." It clearly distinguishes from siblings (pond_get_message, pond_search, pond_sql) by noting tool bodies are one message away and that bulk export should use `pond copy`.

  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?

  Explicitly frames when to use the tool: "the tool for analyzing, reviewing, or summarizing a session," and gives a clear alternative for bulk export. Also explains how to obtain the id from pond_search or a subagent footer, and advises against bulk export, directing to `pond copy`.

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

• pond_sqlA
  4.9/5.0
  Behavior5/5

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

  Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint), the description discloses critical runtime behaviors: output is 'row-capped' with 'long cells clip with a +N chars marker', queries are 'wall-clock-capped', and writes are rejected (in schema description). It also warns about performance pitfalls ('unscoped LIKE over variant_data full-scans and times out') and tells users to scope-then-scan. This goes well beyond annotation hints and prepares the agent for real-world edge cases.

  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, dense paragraph that front-loads purpose and exclusions, then lists use cases, then gives operational guidance and output/performance caveats. Every sentence earns its place; there is no filler or tautology. The structure makes it easy to scan and absorb.

  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?

  Given the tool's complexity (SQL over multiple tables, JSONB fields, export modes, potential for timeouts), the description is remarkably complete. It covers return value behavior (row cap, truncation, export links), performance pitfalls, schema resources to read first, and use-case boundaries. No output schema exists, but nothing is missing for selecting and invoking the tool 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?

  With 100% schema description coverage and highly detailed parameter descriptions, the baseline is 3. The tool description adds usage context for parameters: linking format=parquet|ndjson to avoiding truncation, and timeout_seconds to raising the wall-clock cap for long-running queries. This enriches the bare schema without being essential, so a 4 is appropriate rather than a 5.

  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 clear verb+resource: 'run ONE read-only SQL statement' over specific tables ('sessions / messages / parts'). It explicitly distinguishes itself from siblings by stating 'NOT for finding or reading conversations' and naming pond_search and pond_get_session / pond_get_message as alternatives. This leaves no ambiguity about the tool's niche.

  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 provides explicit when-to-use guidance: 'Reach for SQL only for: aggregation (counts, group-by, joins, time buckets), exact strings or identifiers in conversational text (contains_tokens / fts), tool-call analytics and tool bodies, subagent sessions, bulk export'. It also gives a clear exclusion ('NOT for finding or reading conversations') and names alternative tools, fulfilling the when/when-not/alternatives criteria perfectly.

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