dume_read_adr

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

With no annotations, the description does carry some burden, and it does establish that this is a file-content read from a specific directory (implying read-only, no mutation). However it says nothing about behavior when the ADR id does not exist (error vs empty result), whether content is truncated, or how the path is resolved.

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 lines, front-loaded with the verb and resource, with no filler. The only weakness is the imprecise word 'target', which costs a word without adding information.

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?

An output schema exists, so return-value description is not required, and the file location is a nice touch. But for a tool whose only input is an undocumented identifier with no discovery path among the listed siblings, the definition leaves a real gap in how to call it correctly.

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% and the single parameter adr_id has no description anywhere. The prose mentions 'target ADR' but never says whether adr_id is a filename, a slug, a numeric index, or a path, nor does any sibling tool appear to enumerate valid ADR ids.

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 ('Returns the content') and resource (an ADR markdown file) and even pins the storage location (~/.dume/assets/adrs/), which distinguishes it from siblings like dume_read_state and dume_list_schemas. It stops short of a 5 because 'target' is vague about which ADR is meant and nothing explicitly contrasts it with the other dume_* read tools.

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, no mention of prerequisites, and no hint about where the adr_id comes from. The only implied usage is 'you already have an ADR identifier', which the agent must infer.

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