Frisian MCP (Django)

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

With no annotations provided, the description carries the behavioral disclosure burden. The statement that all reads and writes are real and persistent is a meaningful and important warning about side effects. It could further explain help behavior, continuation semantics, or the full mutation surface, but the core safety-relevant trait is disclosed.

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

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

The description is compact, front-loads the tool's identity, packs the capability groups into a scannable list, and closes with the most important behavioral warning. Every sentence earns its place with no redundancy or filler.

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

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

This is a broad tool with seven parameters, nested objects, no output schema, and no annotations. The description plus the schema's action/params/continuation_token guidance cover capability selection and basic continuation, but the description does not convey an end-to-end call pattern, expected response shape, or how to discover specific actions beyond the help hint in the schema. 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.

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

Schema description coverage is low at 43%, so the description helps by enumerating the concrete resources and groups that can be used inside the params object. It does not explain the mode, page, page_size, or filter_keys parameters, but the schema already provides some structural guidance for those, making the overall parameter context adequate though incomplete.

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

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

The description clearly identifies the tool as a live working demo of frisian-mcp and outlines the three capability groups with their subdomains. This is more than a tautology and helps distinguish the tool as an interactive demonstration surface rather than documentation or setup tooling.

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

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

The wording implies the tool is for hands-on exploration of a live demo system, and the sibling names (docs, install, troubleshooting) make the contrast fairly clear. However, it does not explicitly state when to use this tool versus those siblings, nor does it describe exclusions or recommended first steps.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does list the available actions and their purposes, which is useful, but it does not state whether operations are read-only, how the help flow works, how pagination or continuation tokens behave, or what side effects or auth dependencies exist.

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

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

The description is a single dense, front-loaded sentence with no filler. The action list is compact and each phrase earns its place, though it could have been slightly clearer as a structured list rather than a long comma-separated run-on.

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

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

This is a routing-style tool with 7 parameters, nested objects, and continuation-token mechanics, yet there is no output schema or annotation support. The description covers only action names and omits the invocation patterns needed for pagination, continuation calls, and mode behavior, leaving an agent under-equipped without deep schema inspection.

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

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

Schema description coverage is only 43%, and the description itself does not compensate for the gap. It mentions action names but never explains top-level parameters like mode, page, page_size, filter_keys, or continuation_token, which have non-obvious rules around continuation calls and placement inside params.

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

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

The description clearly identifies the tool as the entry point to frisian-mcp documentation and server guide, and enumerates seven concrete actions with one-line semantic labels. This distinguishes it from siblings like demo, install, and troubleshooting. It loses a point because 'Start here' is an orienting instruction rather than a specific verb+resource statement.

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

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

'Start here' implies this tool should be used first, giving some usage context. However, there are no explicit when-to-use versus when-not-to-use statements, and the description does not clarify when to use the docs tool's demo action versus the sibling demo tool.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It does reveal that the tool returns 'files changed' organized by version and supports semantic search, indicating an informational, read-only purpose rather than an actual installation action. However, it does not explain pagination, continuation tokens, or whether any side effects exist, leaving behavioral gaps.

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

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

The description is a single dense sentence with no filler. It front-loads the core purpose, then lists actions, output format, and search capability. It loses a point for trying to cram multiple concepts (actions, output organization, semantic search) into one sentence without structural separation.

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

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

This tool has 7 parameters, nested objects, a continuation-token mechanism, and no output schema, so the description must explain how to drive the tool correctly. It does not describe mode behaviors, continuation calls, or the relationship between top-level and nested parameters. The undocumented 'query' requirement further decreases completeness.

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

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

Schema coverage is only 43%, so the description needed to compensate. It names the four actions and their outputs, but it introduces a 'query' parameter that does not appear anywhere in the input schema, which is confusing. It also does not clarify the meaning of mode, page, page_size, filter_keys, or continuation_token beyond what the schema already states.

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

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

The description clearly identifies the tool as providing installation guides for specific integrations (nautobot, netbox, paperless, edx) and explains what each action returns. It is distinct from the sibling tools like docs or troubleshooting because it is explicitly installation-focused, though it lacks an explicit verb like 'retrieve' or 'install'.

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

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

The description implies this is the tool to use for installation guidance for the listed integrations, and it mentions semantic search within the section. However, it does not explicitly state when to prefer this over docs, demo, or troubleshooting, nor does it describe the available modes or how pagination/filtering should be used.

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

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 does state that each action returns diagnostic guides and relevant files and that a query enables semantic search, but it omits important behavioral details such as how mode affects output, when pagination or continuation tokens are needed, and what happens when action is omitted or set to 'help'.

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

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

The description is two sentences with no filler, and the core purpose and action list are front-loaded. The note about semantic search is useful, though the detailed parameter semantics were pushed to the schema rather than being summarized here.

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

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

This is a 7-parameter tool with a nested params object, no output schema, and no annotations, so the description must carry a lot of weight. It establishes the tool's purpose and available integrations but omits essential call semantics such as how mode and pagination interact, when continuation_token must be top-level, and what the response structure looks like. An agent would likely need to probe the tool or consult additional documentation before calling it confidently.

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

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

Schema description coverage is only 43%, so the description should compensate, but it only adds 'Pass query for semantic search' and names the four actions. The parameters mode, page, page_size, filter_keys, and continuation_token are not explained in the description, leaving the agent to rely on the sparse schema notes and imperfect inference.

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

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

The description identifies the tool as providing troubleshooting guides for frisian-mcp integrations and explicitly names the four supported actions: nautobot, netbox, paperless, and edx. It is clear that the tool returns diagnostic guides and relevant files for a given integration, which differentiates it from the sibling tools demo, docs, and install. A more explicit verb would make it stronger, but the resource and scope are specific.

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

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

The description does not say when to use this tool versus the sibling tools demo, docs, or install, and it gives no exclusions or alternatives. It implies the tool is for troubleshooting integrations and mentions passing a query for semantic search, but leaves the mode, pagination, and help-action behaviors to inference.

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