Add manual project evidence

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the write/safety profile is covered structurally. The description adds the useful rationale for the default confidence value, but says nothing about the consequences of non-idempotency (e.g., whether repeated calls create duplicate evidence rows) or what the caller gets back, which is the kind of extra context a mutation tool benefits from.

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 tightly written sentences, front-loaded with the verb and resource before the rationale, with no wasted framing. The second sentence slightly duplicates the schema's declared default, but it earns its place by explaining why the default exists.

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?

There is no output schema, so the description is the only place an agent could learn what the call returns, and it is silent on that. It also leaves the spatial/line parameters and sourceType semantics unaddressed, though for a straightforward add operation whose safety profile is covered by annotations, it is minimally adequate.

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 only 43% across 7 parameters, so the description should compensate, but it does not: filePath, lineStart, lineEnd, and sourceType are unexplained in both places. The only parameter reference is the 'inferred' confidence default, which merely restates the schema's own description and enum default.

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 states a specific verb (manually attaches), the resource (an evidence item), and the target (an indexed project), with a concrete example clarifying what counts as manual evidence. The word 'manually' plus the 'indexed project' reference cleanly separates it from automatic extraction siblings like careerproof_index_repository and from retrieval siblings like careerproof_find_evidence.

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 mention of a default 'inferred' confidence because the item 'wasn't pulled directly from a verifiable source' implies this tool is for evidence that cannot be sourced automatically, which hints at when to use it. However, it never explicitly says when to prefer this over careerproof_index_repository or other add_* siblings, nor any prerequisites beyond the implicit need for an indexed project.

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