Graph Paper

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

Annotations already declare this is read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds real behavioral detail: output is Markdown, a known heading returns just that section, and an unknown section returns the heading list instead of erroring.

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 return contract, followed by the section semantics and the routing hint. Slightly dense in the middle but every clause carries information; no 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?

There is no output schema, but the description specifies what the return contains (fields, series types, limits, examples) and how sectioning affects it, which is everything needed to call and interpret the result.

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% and the single parameter is documented, so baseline would be 3. The description adds meaning beyond the schema by illustrating valid values ('Variables', '2D Series Types'), noting omission returns the whole page, and defining the unknown-section fallback.

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 precise verb+resource (return the reference of the Graph Paper plot document format) and enumerates what the reference contains: fields, series types, limits, and examples. It is readily distinguishable from the write-oriented sibling make_plot_link.

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 explicit ordering guidance — 'Read it before you write a document for make_plot_link' — and names the downstream sibling that depends on it. It also explains the fallback behavior for an unrecognized section, so the agent knows how to recover rather than guessing.

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, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: the docs come with titles and JSON and are guaranteed to be valid inputs for make_plot_link, which is behavioral information the annotations do not provide.

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 sentences, both front-loaded with the essential information (what is returned, then how to use it). No filler or redundant restatement of the name.

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?

A zero-parameter, read-only listing tool with an output schema already present; the description need not explain return structure. It still summarizes the payload (title + JSON) and its downstream use, leaving nothing an agent needs 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the schema coverage baseline of 4 applies. No parameter guidance is needed or missing.

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 (return) and resource (example plot documents of the Graph Paper format page), and distinguishes itself from siblings by tying the output to make_plot_link as the consumer. An agent can tell it apart from get_plot_format and make_plot_link without opening any 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?

It gives clear usage context: these are valid inputs for make_plot_link, and the agent should 'start from the one closest to what you want.' It names a downstream alternative tool but does not explicitly state when NOT to use this list tool (e.g., when a format already exists elsewhere).

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?

Beyond the readOnly/idempotent annotations, it discloses genuinely useful behavior: the link is an editable draft, readers need no account, errors are returned as a list of field paths with remediation and no link, and warnings report ignored keys. These failure-mode contracts are exactly what annotations cannot convey.

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?

Four sentences with the purpose front-loaded, followed by input format and then error/warning behavior. Every sentence carries information, though the format reference is repeated from the schema and could be trimmed.

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 structure need not be spelled out, yet the description still covers the meaningful non-happy-path outputs (per-field errors, ignored-key warnings). For a single-parameter validation-plus-link tool, nothing an agent needs is missing.

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% and the single parameter is already documented as a JSON object requiring title and series, including the same pointers to get_plot_format and list_examples. The description largely restates the schema, 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?

The description gives a concrete verb pair and resource: check a Graph Paper plot document and return a link that opens it as an editable draft. The resource is unambiguous, though it does not explicitly contrast itself with get_plot_format or list_examples beyond naming get_plot_format as a format reference.

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?

It clearly explains the expected input (a JSON document in get_plot_format shape) and defines the retry loop: fix reported errors and call again. It stops short of stating when a caller should prefer get_plot_format/list_examples instead, so sibling routing is only implied.

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