Server Quality Checklist

Tool Scores

• gluedly_trigger_scrapeA
  3.6/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full behavioral burden. It discloses the triggering action but does not explain side effects, whether the scrape is asynchronous, whether it returns a snapshot, or whether it overwrites existing data.

  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 concise sentence with no filler. The core action is front-loaded and immediately understandable.

  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 single-parameter trigger tool, the description gives enough for the agent to understand the action and target resource. It could be improved with post-trigger behavior, but the basic invocation context is complete enough.

  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 fully documents page_id as an integer and 'Gluedly page ID' with 100% coverage. The description adds only 'specific' to the parameter context, providing limited additional meaning 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 uses a specific verb, 'Trigger', and a clear resource, 'web scrape execution for a specific Gluedly page ID'. This makes it immediately distinguishable from sibling tools like list_pages and get_snapshot, which imply read/list operations.

  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 context is implied: use this when an immediate scrape of a known Gluedly page is needed. However, the description does not explicitly state when to avoid this tool, what prerequisites exist, or how it relates to list_pages and get_snapshot as an alternative.

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

• gluedly_get_snapshotA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of explaining behavioral traits. 'Fetch' implies read-only behavior, but the description does not explicitly state that this does not trigger a new scrape or that snapshot_id defaults to the latest snapshot when omitted.

  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 sentence with no filler, front-loading the key action and the two useful return modes. It is compact but still informative enough to be scannable.

  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 parameter schema handles the input requirements well, and the description identifies the main output forms, but no output schema and no annotations leave the tool lifecycle unclear. The description could better say whether the snapshot must already exist and how this tool relates to trigger_scrape.

  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%, so the parameters page_id, format, and snapshot_id already have clear descriptions. The description adds a small semantic layer by explaining the return options, but it does not significantly go beyond what the schema already provides.

  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 names the action ('Fetch'), the resource ('a page snapshot'), and the two output forms ('clean extracted rows' or 'prompt-ready Markdown'). This clearly distinguishes the tool from the sibling tools: it is about retrieving snapshot data, not listing pages or triggering a new scrape.

  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 intended usage is implied: call this tool when you want the extracted content from an existing page snapshot. However, the description does not explicitly say to use gluedly_trigger_scrape when a fresh snapshot is needed, nor does it mention the lifecycle between creating and fetching a snapshot.

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

• gluedly_list_pagesA
  3.8/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'Retrieve all mapped scraping pages' and does not describe return format, pagination, permissions, stability, or any side effects. For a zero-parameter read operation this is a notable but not severe gap.

  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 word contributes to explaining the tool's action and scope.

  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 simplicity (no parameters, no nested structure, no output schema), the description is mostly complete for invoking the tool. However, it lacks detail about what a returned page representation looks like, which an agent might need for downstream steps.

  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?

  The tool has zero parameters, and the input schema covers everything by being empty. There is no parameter semantics to explain, so the description does not need to provide additional parameter detail. The baseline for a zero-parameter tool 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 uses a specific verb ('Retrieve') and a clear resource ('all mapped scraping pages in your Gluedly workspace'), which also differentiates it from the sibling tools that trigger scrapes or get snapshots. The scope is unambiguous even without a title.

  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 description implies use when you need to list all mapped pages, but it does not provide explicit when-to-use guidance or contrast with the siblings (e.g., when to trigger a scrape or get a snapshot instead). No exclusions or alternatives are mentioned.

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