Line9

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

Annotations already cover the read-only/idempotent/non-destructive profile, but the description goes well beyond that: it discloses the auth requirement, the hard capability limit (no publish or save), the side-effect-free nature of edits unless the line9: frontmatter is preserved, and the identity-stamping consequence of dropping that block. This is exactly the kind of mutation-adjacent context annotations cannot express.

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?

Front-loaded with the core action, then layered with the frontmatter warning and capability limits; every sentence carries information relevant to calling it correctly. It is dense but not padded, though the CLI aside is slightly tangential to the call itself.

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?

With an output schema present, return values need not be explained, and the description still extends it by noting the rendered view and the open_url link. Auth, capability boundaries, and the identity-preservation caveat are all covered, leaving nothing an agent needs in order to call it correctly.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents 'name, slug, or trailing public_ref'. The description repeats 'by name or slug' but adds no format or resolution-order detail beyond the schema — baseline 3.

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?

States a specific verb (fetch) and resource (a published diagram's Mermaid source) with both lookup modes (name or slug) and the rendering behavior. It is clear on its own, but it never names or distinguishes itself from the siblings list_diagrams and render_diagram, and 'show it rendered' arguably overlaps with render_diagram's territory.

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?

Gives real usage context: Line9 sign-in is required, the connector cannot publish or save, and the publish workflow is via the Line9 UI/open_url rather than the CLI. It stops short of routing between sibling tools (when to call this vs render_diagram vs list_diagrams), which keeps it out of the top band.

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?

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful prerequisite the annotations cannot express: 'Requires Line9 sign-in.' It does not discuss pagination or result ordering, but the auth note is real added value for a read tool.

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?

Two tight sentences: the first states what is returned, the second states when to call it, followed by the auth prerequisite. Nothing is padded and the most important content (scope and returned fields) is front-loaded.

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?

An output schema exists, so the field list in the description is a bonus rather than a necessity, and the auth requirement is the key operational caveat. The definition is essentially complete for a two-parameter, zero-required-parameter list tool, with only minor omissions like result ordering or pagination behavior.

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 100% – limit (1–100, default 50) and query (case-insensitive substring of diagram name) are fully documented in the schema. The description adds no additional semantics for either parameter, so the baseline 3 applies.

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?

Names a specific verb and resource ('List the diagrams published in the user's Line9 workspace(s)'), enumerates the returned fields, and differentiates itself from the sibling get_diagram by positioning itself as the discovery step before it. An agent can tell what this does and where it sits in the workflow 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.

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

Gives an explicit use case ('Use it to find a diagram before `get_diagram`'), establishing the ordering relative to a sibling. It does not address render_diagram or state when not to use this tool (e.g. when the diagram id is already known), so it falls short of full when/when-not coverage.

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?

Annotations already declare read-only/idempotent, but the description goes well beyond: environment-dependent behavior (panel vs terminal), the watermark rule, no sign-in requirement, and the error-recovery loop. The 'cannot publish or save' limitation is consistent with readOnlyHint and adds real operational context.

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?

Front-loaded with purpose and trigger, then logically sequenced through output, errors, environment, styling and auth. It is long, but the complexity justifies most of it; the publishing sentence partly repeats 'cannot publish or save' and could be tightened.

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?

Output schema exists, yet the description still frames the verdict and error shape usefully, and it covers auth, environment handling, styling, and limitations. An agent has everything needed to call it correctly and to act on the result in either UI mode.

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 100%, so baseline is 3; the schema already documents frontmatter, theme values and the max length. The description reinforces the styling directive ('set... in the source itself... never as arguments') but never mentions the opaque `plan` parameter and largely restates schema content rather than adding new semantics.

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?

States a specific verb and resource — 'Render Mermaid source with Line9's layout engine' — and is immediately distinguishable from get_diagram/list_diagrams, which are retrieval rather than rendering. It also scopes which Mermaid kinds get native layout versus Mermaid's own, so the agent knows exactly what the tool produces.

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?

Gives a clear trigger ('Call this whenever you write or change Mermaid and the user should see the result') and an explicit when-not ('This connector cannot publish or save... not with the Line9 CLI'). It does not name the sibling tools as alternatives for read/retrieve cases, so the routing advice is strong but not fully closed.

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