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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered without help from the description. The description adds real value by disclosing what the diagram must contain (concrete numeric example and the analogy failure boundary), but says nothing about the rendered output form (image, SVG, mermaid, markup) or whether rendering can fail.

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?

A single front-loaded sentence with no filler: verb, artifact, and contents in one pass. It is efficient, though for a seven-parameter rendering tool it is arguably too terse to be fully 'appropriately sized'.

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?

No output schema exists, so the description carries the burden of saying what a 'render' returns, and it does not. For a tool with seven required structured inputs sitting among four similar render_* siblings, the agent is left without return-format or routing information.

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 71% and every one of the seven required parameters carries its own description, so the schema does most of the work. The description only gestures at the parameter set (类比, 例子, 失效边界) without adding format, sizing, or dependency rules (e.g. 1-3 mappings, 2-4 mechanism steps) beyond what the schema enforces.

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 names a specific verb (绘制/render) and a specific artifact (生活类比↔科学机制映射图) plus the required contents (具体例子、类比失效边界), so an agent knows exactly what gets produced. It does not, however, distinguish itself from the four sibling render_* tools (paper map, section flow, formula structure, evidence prism), which is the one thing an agent must decide between here.

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?

There is no statement of when to choose this over render_paper_map, render_section_flow, render_formula_structure, or render_evidence_prism, and no prerequisites or trigger conditions. The only hint is the phrase 晦涩概念, which weakly implies the tool targets hard-to-grasp concepts, but no explicit guidance or exclusion is given.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety and idempotency profile is fully covered. The description adds the conceptual output structure (three evidence facets), which is useful, but says nothing about rendering behavior, output form, or limits beyond what annotations carry.

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?

A single tightly written sentence with the verb+resource front-loaded and the three facets enumerated efficiently. Nothing is redundant, though the extreme brevity leaves no room for the routing context an agent would also want.

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?

For a read-only rendering tool with five fully documented required parameters and a complete safety annotation set, the description is nearly sufficient; 'draw' plus the named facets convey what is produced. It could say more about the output artifact, but no output schema exists and none is strictly required here.

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% with per-field descriptions and length bounds, so the schema does the heavy lifting. The description names the three content facets (look_at/supports/cannot_conclude) but adds no syntax, format, or constraint detail beyond what the schema already provides.

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 states a specific verb (绘制/draw) and a specific resource (图表证据三棱镜/chart evidence prism), and unpacks it into three concrete facets: what to look at, what it supports, what it cannot conclude. It is clear what the tool does, but it does not explicitly distinguish itself from the sibling render_* tools (render_paper_map, render_section_flow, etc.), so it stops short of a 5.

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 gives no when-to-use, when-not-to-use, or alternative-selection guidance. '阻止过度推断' (prevent over-inference) hints at the goal but not at the scenario or the sibling it competes with, leaving the agent to infer when to pick this over render_concept_diagram or render_paper_map.

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, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered structurally. The description adds a content contract (must preserve known conditions, numeric verification, and non-holding cases) but discloses nothing beyond annotations about rendering behavior, auth, or limits. This is additive but modest against an annotation-covered tool, and there is no contradiction.

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?

A single front-loaded sentence with the core action first and the requirements after a semicolon; nothing is padded. It is perhaps over-compressed for a seven-required-parameter tool, but every clause carries content.

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 no output schema, the description carries the burden of explaining what the rendered artifact is, yet it gives only a terse '符号卡+逐步运算图' sketch. For a seven-required-parameter tool with strict length caps on every field, the description is minimally adequate but leaves the return shape and depth of rendering unclear.

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 71%, so the schema largely documents the seven required fields already. The description loosely maps to three of them (已知条件、数字验算、不成立的情形 ≈ numeric_example, limitation, and conditions), adding only marginal meaning over the schema's own per-field descriptions.

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 states a specific verb and output form: rendering a key formula as a symbol card plus a step-by-step computation diagram, which distinguishes it from render_concept_diagram and render_section_flow by content type. It is clear but never names or contrasts a sibling explicitly, so differentiation is inferred from the word 'formula' rather than stated.

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 text is a set of content requirements ('必修保留已知条件、数字验算及不成立的情形'), not guidance on when to choose this tool over the sibling render_* tools. There is no stated condition, trigger, or exclusion that tells an agent when render_formula_structure is the right pick versus render_evidence_prism.

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 cover the safety profile (readOnly, idempotent, non-destructive). The description adds genuine behavioral context beyond them: the output is a visible PNG image, titles and causal arrows must not be fabricated, and a source note is mandatory. It still omits error behavior and output limitations, but it adds real value on top of the annotations.

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?

A single dense sentence with the purpose front-loaded and two semicolon-separated constraints. Every clause earns its place and there is no filler, though the telegraphic style is terse.

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?

For a six-parameter rendering tool with no output schema, the description correctly discloses the PNG output format and the mandatory source_note, but leaves the meaning and interplay of relationships, nodes, current_index, and subtitle unaddressed, so it is only partially 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 coverage is only 50%, so the description must carry more weight, but it only reinforces that source_note is required and hints that titles must be real (matching the nodes.title 'cannot fabricate' constraint). It says nothing about nodes, relationships, current_index, or subtitle structure, leaving half the parameter surface unexplained.

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 states a specific verb+resource: converting verified paper section responsibilities into a visible PNG argument-flow diagram. This is concrete enough to distinguish it from most siblings, though it does not explicitly differentiate itself from the similar-sounding render_section_flow.

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 constraints (no fabricated titles or causal arrows; source_note is mandatory) which imply the tool should be used only on verified content, but it never states when to choose this over render_section_flow, render_evidence_prism, or the other render_* siblings. Usage is implied, not directed.

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 readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds the genuinely useful disclosure that it returns a real PNG image (important with no output schema, distinguishing it from a tool that merely returns a spec), plus the 2–7 step constraint.

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?

A single front-loaded sentence that packs the output type, the step range, and the per-step content with 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?

For a 5-parameter tool with no output schema, stating the PNG return is a good start, but current_index (a 0–6 index into the stages) is left entirely undefined, and there is no note on how the input stages/relationships shape the rendered layout. Adequate but with a real gap.

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 40%, so the description carries extra burden. It does map '每步任务' to the per-stage fields and '承接关系' to relationships, and restates the 2–7 stage bound, but current_index and section_title semantics are never explained in either place.

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 states a specific verb and resource (画…流程图 / draw a section flow diagram), bounds the scope to 2–7 steps, and names the content carried by each step (task + connecting relationships). It is clearly distinguishable from render_formula_structure or render_concept_diagram by resource, though it never explicitly names those siblings.

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?

There is no when-to-use or when-not-to-use guidance and no mention of the sibling render_* tools, even though the family contains four close alternatives. Usage is only implied by the resource name.

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