add_dependency

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

Annotations already declare this a non-read-only, non-idempotent, non-destructive mutation, and the description adds that a dependency edge is what gets persisted plus a hard evidence requirement. It does not disclose what happens on a duplicate add (relevant given idempotentHint=false) or whether the edge affects blast-radius/incident analysis.

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 short sentences, the core action first and the evidence constraint second; nothing is wasted or buried.

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?

Adequate for a simple 4-param mutation with no output schema, but an agent still lacks guidance on the undocumented `optional` flag, duplicate handling, and whether recorded edges are validated or rejected when inconsistent.

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 0%, so the description must carry the parameter burden. It usefully defines caller, callee, and the expected evidence format (file and key or line), but leaves the `optional` boolean completely 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?

States a specific verb and resource — recording a caller→callee edge — which is clearly distinct from read-side siblings like trace_dependency_path, query_graph, and get_blast_radius. It stops short of explicitly naming those siblings as the read-only alternative.

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?

Usage is only implied by the name and the write semantics; the description never says when to add a dependency versus querying the graph, nor whether duplicates or self-edges are acceptable. The one constraint given ('evidence must say where you saw it') is a parameter requirement rather than a when-to-use rule.

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