save_finding

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

With no annotations, the description carries the full behavioral burden and mostly does not: it implies a mutation but never says whether an existing finding is overwritten, deduplicated, or appended, nor what permissions or workspace scoping are required. "Attributed" hints at provenance tracking but is not defined. For a persistent write tool this leaves the safety and side-effect profile unclear.

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 or repetition. It is efficient, though its brevity is part of the completeness problem rather than a virtue on its own.

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 four-parameter persistent write operation with no annotations, no output schema, and zero schema documentation, one sentence is not sufficient. Nothing tells the agent what a successful save produces or how to recover from a malformed finding.

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% across four parameters, so the description must compensate and does not. It never explains what "function" identifies, how "symbols" relates to it, what belongs in "notes", or whether "workspace" defaults to the active workspace—the words "attributed" and "workspace" gesture at these fields without defining them.

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 specific verb ("persist"), a specific resource ("reverse-engineering finding") and a destination ("workspace knowledge graph"), which is enough to separate it from read-oriented siblings like graph_query_neighbors. However, it never names its closest siblings (graph_node_upsert, equivalence_record) so the agent must infer why this write path exists rather than another.

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 guidance, no precondition (e.g. does the workspace need to exist?), and no mention of any alternative tool. The agent is left to guess when a finding should be saved here versus recorded via graph_node_upsert or equivalence_record.

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