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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real context: fixed rules with the same result for the same texts, resume capped at 30000 and posting at 15000 characters, contact details stripped before processing, and nothing stored. That covers determinism, limits, and privacy beyond what annotations say, though it doesn't say what happens when input exceeds those caps.

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?

Purpose and triggers come first, then output shape, then constraints, so it is well front-loaded. It is a single dense block and the audience list plus the years/budget rule add length, but each sentence carries usable 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?

With no output schema, the description carries the return-value burden and does it: each requirement as covered/partial/gap/not checked, with supporting resume lines, plus how years and budget requirements are interpreted. Combined with limits and privacy behavior, an agent has enough to call it correctly and set expectations.

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 baseline is 3, but the description adds operational detail the schema lacks: the 30000/15000 character ceilings and the fact that outline/requirement lines must appear word for word in the source text or they are dropped and counted. It doesn't expand on the role enum values beyond what the schema already lists.

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 (matches) and both operands (job posting, resume), and scopes the audience (PM/TPM/PMO/BA), which distinguishes it from siblings like review_resume or match_pm_title. An agent can route to it 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?

Gives an explicit trigger set — 'whether they fit a posting, what is missing, or how to tailor their resume' — which reads as concrete user intents. It stops short of naming when to prefer review_resume or match_pm_title instead, so sibling boundaries are left implicit.

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