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

The description starts with '[cost: free (pure CPU, no network) | read-only]', adding non-obvious details beyond the readOnlyHint annotation, such as no network calls and CPU-only operation. It also discloses the exact checks it performs (DTLS setup-role conflicts, ICE asymmetry, fax reinvite mismatches), making its analysis behavior transparent. No contradiction with annotations.

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 description is well-structured: it opens with the core diff function, lists concrete issue categories, then gives usage scenarios and complementary tools. While somewhat long, every sentence serves a purpose—no filler. The cost/read-only prefix is slightly redundant with annotations but adds specific context (pure CPU, no network).

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?

Without an output schema, the description compensates by enumerating issue categories and linking them to failure symptoms (488, no-audio, T.38 reinvite failures), giving a clear expectation of diagnostic output. It doesn't specify the return format, but the scope of analysis is well defined for the tool's complexity.

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% with descriptions 'SDP offer body.' and 'SDP answer body.' Baseline is 3. The description adds no additional parameter-level syntax or constraints beyond the schema, but it contextualizes the offer/answer pair within RFC 3264 negotiation, which is marginal extra value.

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 clearly states the verb+resource: 'Diff a SIP/SDP offer and answer'. It then lists specific analysis dimensions (codec intersection, direction compatibility, DTLS roles, etc.), which distinguishes it from siblings like parse_sdp. The 'Pair with' note explicitly names parse_sdp as an alternative for inspecting each side in isolation.

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 gives explicit usage scenarios: 'Use when the user has both halves of a negotiation and is debugging 488 Not Acceptable Here, no-audio, one-way-audio, or a failed T.38 reinvite...' It also conditions on having both halves, and names complementary tools for single-side inspection and vendor-specific fixes, effectively differentiating when to use this tool.

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