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

With no annotations, the description carries the full burden and does well: it discloses rate limiting (≤30/hour/key → 429), tenant scoping (no cross-tenant), that raw media stays client-side, that audit records are durable, and that it is a managed pointer only, not a legal deletion SLA. Missing only the response shape, which is minor for a mutation.

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?

The dense first line is front-loaded and information-rich, but the description then repeats itself substantially in the second block (E.3 section restates KVKK-first redaction, tenant scope, durable audit, and the non-SLA caveat already given). This redundancy costs it, though the total length remains manageable.

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 six-parameter mutation tool with no annotations and no output schema, the description covers the critical behavioral facts an agent needs: scope, side effects, rate limit, audit, and limitations. The only gap is explicit response/return guidance and a named alternative, both minor here.

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 100%, so the schema already documents all six parameters (mode, phone, target_id, target_type, who, reason). The description adds context on mode values and lookup-by-target_id-or-phone, but nothing beyond what the schema provides. Baseline 3 is correct.

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 (redact/forget) and resource (derived index documents by id or phone), plus the KVKK compliance framing. It is distinct from siblings like pbx_persons_get or pbx_index_partial, though it doesn't name a sibling directly. The purpose is clear enough without opening the schema.

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 description implies when to use it (KVKK-first forget, managed SaaS) and mentions a companion list endpoint (GET /v1/pbx/redact/audit, sibling pbx_redact_audit), but gives no explicit when-not-to-use or prerequisite conditions. Usage is inferable but not spelled out.

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