mutate_graph

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

No annotations exist, so the description carries the full burden. It does disclose a key behavioral trait — that successful mutations persist to disk immediately — but says nothing about reversibility, what happens on a failed or partial mutation, idempotency of duplicate add_node/add_edge calls, or whether the in-memory graph must be refreshed via reload_graph afterward.

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: the first commits to what the tool is, the second is a tightly parallel action-by-action breakdown. Every clause earns its place and the general purpose is front-loaded before the detail.

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 12-parameter tool with conditional per-action fields and no annotations or output schema, the description covers the action taxonomy and persistence but leaves real gaps: no per-action parameter requirements, no indication of what is returned on success, and no mention of interaction with the sibling reload_graph.

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%, so the schema already documents all 12 parameters, which sets the baseline at 3. The description adds action-level semantics that the flat schema enum does not (what each action accomplishes), but it never states which parameters are conditionally required per action — e.g. that add_edge needs source/target or that remove_edge accepts an optional relation filter.

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+resource ('apply a manual mutation to the relational index') and then enumerates all four actions with concrete semantics (add_node registers a concept/rationale, add_edge records a verified relationship, remove_edge deletes a stale edge, recluster re-runs community detection). This clearly separates it from read-oriented siblings like query_graph, get_graph_info, and inspect_symbol.

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?

Each action value is paired with the situation that selects it (e.g. remove_edge for 'a stale or false-positive edge', recluster to 're-run community detection'), which is strong intra-tool routing. However, there is no guidance on when to prefer this over the write-ish sibling add_planned_symbol, nor any exclusion such as 'do not use for bulk imports — use reload_graph instead'.

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