graph_depend

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the agent knows this is a mutating operation. The description adds one genuinely useful behavioral fact — the edge only affects scheduling order once the direction is confirmed — but it never explains the destructive side (does recording overwrite an existing edge?), nor permission or validation requirements, despite carrying a destructiveHint.

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 short sentence with the scheduling caveat front-loaded in the parenthetical — nothing wasted and no filler. It is arguably too terse for a 7-parameter mutating tool, but as pure structure it is clean and readable.

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 7-parameter, destructive, no-output-schema mutation, one line is thin. It does not say what confirmation entails, whether repeated calls overwrite, what happens with the default 'agent' direction, or how it relates to graph_undepend/graph_dependencies. The scheduling note is the only substantive context provided.

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%, so every parameter including the direction enum and its 'only control_flow/agent participate in sorting' note is already documented. The description merely restates the direction/scheduling relationship rather than adding syntax, defaults, or examples beyond the schema.

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+resource pair ('记下/确认一条依赖边' – record/confirm a dependency edge), which is enough for an agent to distinguish it from siblings like graph_undepend (removal), graph_dependencies (listing), and graph_node. It does not explicitly contrast itself with those siblings, but the action is unambiguous.

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 parenthetical '（确认方向后它才参与调度排序）' hints at the condition under which the edge becomes effective for scheduling, which is a usage-relevant cue. However there is no explicit when-to-use statement, no prerequisite (e.g. must graph_node exist first?), and no direction on choosing between graph_depend and graph_undepend when an edge already exists.

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